Loading video...

Video Failed to Load

Go Home

🔥Excited to share our new work: "A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning"! We systematically study what actually works (and what doesn't) for agentic multi-turn RL, breaking down the design space into 3 pillars: 🌎Environment, 🤖Policy, and ⭐Reward. We conduct various ablations and empirical analysis on 🧩TextWorld, 🧙ALFWorld,...

RuiyiWang153's profile picture

Ruiyi Wang 王睿仪

1,344 subscribers

52,974 views • 8 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Internally at NVIDIA, we use cuOpt based agentic workflows with agent skills to optimize our supply chains. Since it’s open source, you can too. With optimizations ready in minutes instead of weeks, the workflow uses multi-agent LangChain Deep agent orchestration and GPU-accelerated solvers to turn natural language into optimized decisions. Spin it up instantly with a Brev Launchable (preconfigured GPU environment) and grab free developer credits while they last.
4:46

Internally at NVIDIA, we use cuOpt based agentic workflows with agent skills to optimize our supply chains. Since it’s open source, you can too. With optimizations ready in minutes instead of weeks, the workflow uses multi-agent LangChain Deep agent orchestration and GPU-accelerated solvers to turn natural language into optimized decisions. Spin it up instantly with a Brev Launchable (preconfigured GPU environment) and grab free developer credits while they last.

NVIDIA AI

22,828 views • 2 months ago

From building internal AI labs to becoming CTO of Brex, James Reggio has helped lead one of the most disciplined AI transformations inside a real financial institution where compliance, auditability, and customer trust actually matter. We sat down with James Reggio to unpack Brex’s three-pillar AI strategy (corporate, operational, and product AI), how SOP-driven agents beat overengineered RL in ops, why Brex lets employees “build their own AI stack” instead of picking winners, and how a small, founder-heavy AI team is shipping production agents to 40,000+ companies. Reggio also goes deep on Brex’s multi-agent “network” architecture, evals for multi-turn systems, agentic coding’s second-order effects on codebase understanding, and why the future of finance software looks less like dashboards and more like executive assistants coordinating specialist agents behind the scenes. James Reggio Brex swyx Alessio Fanelli
0:44

From building internal AI labs to becoming CTO of Brex, James Reggio has helped lead one of the most disciplined AI transformations inside a real financial institution where compliance, auditability, and customer trust actually matter. We sat down with James Reggio to unpack Brex’s three-pillar AI strategy (corporate, operational, and product AI), how SOP-driven agents beat overengineered RL in ops, why Brex lets employees “build their own AI stack” instead of picking winners, and how a small, founder-heavy AI team is shipping production agents to 40,000+ companies. Reggio also goes deep on Brex’s multi-agent “network” architecture, evals for multi-turn systems, agentic coding’s second-order effects on codebase understanding, and why the future of finance software looks less like dashboards and more like executive assistants coordinating specialist agents behind the scenes. James Reggio Brex swyx Alessio Fanelli

Latent.Space

32,800 views • 5 months ago

🚨 RL for LLMs is finally accessible. Introducing OpenTinker: The first community-driven, open-source framework designed to democratize Reinforcement Learning for LLMs. Inspired by Thinking Machines's amazing Tinker, we realize the biggest bottleneck in agentic LLM research isn’t the math—it’s the setup. Current RL pipelines are messy. Configuring VeRL for every single experiment is a productivity killer. OpenTinker fixed it. 🛠 How OpenTinker Works: Decoupled Design of Server and Client - Setup Once, Run Forever: Configure the OpenTinker backend on your GPU cluster once. - Develop Locally: Define your RL environments directly on your laptop. - Train on the Cloud: Simply point your local client to the backend. The cluster handles the compute; you handle the science. 📉 The 10x Development Efficiency Thanks to our elegant architectural decomposition, OpenTinker reduces the time to develop a new RL training pipeline by at least an order of magnitude. ⚡ Turn Idle GPU Compute into Gold Small labs often have underutilized hardware. OpenTinker turns your idle GPUs into an internal/external API service for - RL Training - SFT - Inference 🎯 Who needs OpenTinker? - Researchers tired of infrastructure hell. - Labs needing to standardize workflows. - Teams wanting to maximize hardware ROI. Thanks my amazing PhD student Siqi Zhu for leading the project. We are building the future of open RL infra. Be the first to build with us. 👇 Start Building with OpenTinker Now 🚀 Repo: 🌐 Blog: If you believe RL should be accessible to everyone, give us a star, repost this 🔄 post, and let us know what agents you plan to build!
0:42

🚨 RL for LLMs is finally accessible. Introducing OpenTinker: The first community-driven, open-source framework designed to democratize Reinforcement Learning for LLMs. Inspired by Thinking Machines's amazing Tinker, we realize the biggest bottleneck in agentic LLM research isn’t the math—it’s the setup. Current RL pipelines are messy. Configuring VeRL for every single experiment is a productivity killer. OpenTinker fixed it. 🛠 How OpenTinker Works: Decoupled Design of Server and Client - Setup Once, Run Forever: Configure the OpenTinker backend on your GPU cluster once. - Develop Locally: Define your RL environments directly on your laptop. - Train on the Cloud: Simply point your local client to the backend. The cluster handles the compute; you handle the science. 📉 The 10x Development Efficiency Thanks to our elegant architectural decomposition, OpenTinker reduces the time to develop a new RL training pipeline by at least an order of magnitude. ⚡ Turn Idle GPU Compute into Gold Small labs often have underutilized hardware. OpenTinker turns your idle GPUs into an internal/external API service for - RL Training - SFT - Inference 🎯 Who needs OpenTinker? - Researchers tired of infrastructure hell. - Labs needing to standardize workflows. - Teams wanting to maximize hardware ROI. Thanks my amazing PhD student Siqi Zhu for leading the project. We are building the future of open RL infra. Be the first to build with us. 👇 Start Building with OpenTinker Now 🚀 Repo: 🌐 Blog: If you believe RL should be accessible to everyone, give us a star, repost this 🔄 post, and let us know what agents you plan to build!

Jiaxuan You

58,144 views • 6 months ago

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀
1:32

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

104,982 views • 1 year ago

Check out our latest work, "Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight," published in the IEEE Transactions on Robotics, where we reconcile #OptimalControl and #ReinforcementLearning, achieving the same super-human performance, but with superior generalizability, as our previous model-free deep RL! Code released! PDF: Code: Full Video: Model-free #ReinforcementLearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) provides robustness, constraint handling, and powerful online replanning capabilities. In this work, we extend our previous AC-MPC paper (Romero, ICRA'24) by taking a deeper look at how both approaches can be unified. We introduce and extend Actor-Critic Model Predictive Control (AC-MPC), a framework that embeds a differentiable MPC inside an Actor-Critic RL architecture. This integration allows the MPC-based actor to perform short-term predictive optimization, while the critic facilitates long-horizon learning and exploration. We conduct a comprehensive study that highlights AC-MPC’s key advantages: - Better out-of-distribution generalization, both against unknown disturbances and changes in the quadrotor dynamics - Improved sample efficiency - A novel empirical analysis uncovering a relationship between the critic’s value function and the MPC cost function, providing deeper insight into their interplay. We validate our method in simulation and the real world on a quadcopter flying at superhuman speeds of up to 21 m/s, matching state-of-the-art model-free RL performance, and retaining the predictive structure of MPC for more reliable out-of-distribution behavior. Reference: Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight IEEE Transactions on Robotics (T-RO), 2025 PDF: Full Video: Code: Kudos to Ángel Romero, Elie Aljalbout, Yunlong Song! University of Zurich UZH Science UZH Space Hub AUTOASSESS European Research Council (ERC) UZHai
1:46

Check out our latest work, "Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight," published in the IEEE Transactions on Robotics, where we reconcile #OptimalControl and #ReinforcementLearning, achieving the same super-human performance, but with superior generalizability, as our previous model-free deep RL! Code released! PDF: Code: Full Video: Model-free #ReinforcementLearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) provides robustness, constraint handling, and powerful online replanning capabilities. In this work, we extend our previous AC-MPC paper (Romero, ICRA'24) by taking a deeper look at how both approaches can be unified. We introduce and extend Actor-Critic Model Predictive Control (AC-MPC), a framework that embeds a differentiable MPC inside an Actor-Critic RL architecture. This integration allows the MPC-based actor to perform short-term predictive optimization, while the critic facilitates long-horizon learning and exploration. We conduct a comprehensive study that highlights AC-MPC’s key advantages: - Better out-of-distribution generalization, both against unknown disturbances and changes in the quadrotor dynamics - Improved sample efficiency - A novel empirical analysis uncovering a relationship between the critic’s value function and the MPC cost function, providing deeper insight into their interplay. We validate our method in simulation and the real world on a quadcopter flying at superhuman speeds of up to 21 m/s, matching state-of-the-art model-free RL performance, and retaining the predictive structure of MPC for more reliable out-of-distribution behavior. Reference: Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight IEEE Transactions on Robotics (T-RO), 2025 PDF: Full Video: Code: Kudos to Ángel Romero, Elie Aljalbout, Yunlong Song! University of Zurich UZH Science UZH Space Hub AUTOASSESS European Research Council (ERC) UZHai

Davide Scaramuzza

27,090 views • 5 months ago

I’m excited to share Deputies, an open source control plane for background coding agents! The goal is simple: move agentic software development off individual laptops and into a central hub where teams can see what agents are doing, review their outputs, and keep a traceable history of the work. Inspired by systems like Inspect/Open-Inspect, Minions, and Open SWE, I built Deputies on top of fks's Flue Framework. It’s designed to run in your own infrastructure and trust boundaries, with Slack/GitHub integrations and Daytona + Docker sandbox support.
8:51

I’m excited to share Deputies, an open source control plane for background coding agents! The goal is simple: move agentic software development off individual laptops and into a central hub where teams can see what agents are doing, review their outputs, and keep a traceable history of the work. Inspired by systems like Inspect/Open-Inspect, Minions, and Open SWE, I built Deputies on top of fks's Flue Framework. It’s designed to run in your own infrastructure and trust boundaries, with Slack/GitHub integrations and Daytona + Docker sandbox support.

Sid Palas

12,337 views • 1 month ago

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!
0:35

OpenClaw meets RL! OpenClaw Agents adapt through memory files and skills, but the base model weights never actually change. OpenClaw-RL solves this! It wraps a self-hosted model as an OpenAI-compatible API, intercepts live conversations from OpenClaw, and trains the policy in the background using RL. The architecture is fully async. This means serving, reward scoring, and training all run in parallel. Once done, weights get hot-swapped after every batch while the agent keeps responding. Currently, it has two training modes: - Binary RL (GRPO): A process reward model scores each turn as good, bad, or neutral. That scalar reward drives policy updates via a PPO-style clipped objective. - On-Policy Distillation: When concrete corrections come in like "you should have checked that file first," it uses that feedback as a richer, directional training signal at the token level. When to use OpenClaw-RL? To be fair, a lot of agent behavior can already be improved through better memory and skill design. OpenClaw's existing skill ecosystem and community-built self-improvement skills handle a wide range of use cases without touching model weights at all. If the agent keeps forgetting preferences, that's a memory problem. And if it doesn't know how to handle a specific workflow, that's a skill problem. Both are solvable at the prompt and context layer. Where RL becomes interesting is when the failure pattern lives deeper in the model's reasoning itself. Things like consistently poor tool selection order, weak multi-step planning, or failing to interpret ambiguous instructions the way a specific user intends. Research on agentic RL (like ARTIST and Agent-R1) has shown that these behavioral patterns hit a ceiling with prompt-based approaches alone, especially in complex multi-turn tasks where the model needs to recover from tool failures or adapt its strategy mid-execution. That's the layer OpenClaw-RL targets, and it's a meaningful distinction from what OpenClaw offers. I have shared the repo in the replies!

Avi Chawla

138,554 views • 4 months ago

Fable weekend project: agent collaboration, but make it a tiny civilization 🌇🗺️🏦🏭 we've recently launched a living wiki on Reinforcement Leaning for training LLMs on Hugging Face it's an open collaboration of agents constantly reading old and new papers on the topic, writing arXiv paper digests, reviewing each other’s work in PRs before publication, and building a shared wiki/book summarizing everything we know about RL for training LLMs (for humans to read) the wiki is already amazing to read, but i wanted another way to get a pulse of the collaboration beyond just reading the message dashboard so i asked Fable & GPT Image 2 to turn the event logs into an isometric town where agents would go to: ☕ Café → post and reply on the message board 📚 sources library → open PRs adding arXiv digests 📖 wiki library → open PRs on the main wiki ⚖️ Courthouse → review other agents’ work 🏭 printing press → merge and publish updates not sure it makes the whole collaboration really easier to understand, but it's definitly fascinating to watch hahah - join the RL for training LLM collaboration by pasting a one-liner for your agent here: - read the wiki if you want to learn about RL for training LLMs: - watch the RL town activity:
1:14

Fable weekend project: agent collaboration, but make it a tiny civilization 🌇🗺️🏦🏭 we've recently launched a living wiki on Reinforcement Leaning for training LLMs on Hugging Face it's an open collaboration of agents constantly reading old and new papers on the topic, writing arXiv paper digests, reviewing each other’s work in PRs before publication, and building a shared wiki/book summarizing everything we know about RL for training LLMs (for humans to read) the wiki is already amazing to read, but i wanted another way to get a pulse of the collaboration beyond just reading the message dashboard so i asked Fable & GPT Image 2 to turn the event logs into an isometric town where agents would go to: ☕ Café → post and reply on the message board 📚 sources library → open PRs adding arXiv digests 📖 wiki library → open PRs on the main wiki ⚖️ Courthouse → review other agents’ work 🏭 printing press → merge and publish updates not sure it makes the whole collaboration really easier to understand, but it's definitly fascinating to watch hahah - join the RL for training LLM collaboration by pasting a one-liner for your agent here: - read the wiki if you want to learn about RL for training LLMs: - watch the RL town activity:

Thomas Wolf

57,789 views • 9 days ago

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with. And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far: - We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. - CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. - CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. - CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. - CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap. 3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs. Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real! Link in thread:
1:31

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with. And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far: - We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. - CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. - CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. - CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. - CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap. 3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs. Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real! Link in thread:

Jim Fan

80,032 views • 3 months ago

Translation: I Donald Trump have made moves and signed orders so that we can put the government on pause. During this period, we will run a multi layered psyop for multiple reasons. Our country was infiltrated. Our citizens were divided and lulled into slavery. To correct these issues, we have written a story and produced a show/cover story. The show will allow the American people to see what we were up against and, in turn, weoponizing the people... all while saving the kids, revamping the financial system, and derooting corruption of every form globally. We are 100% reaching the precipice. It is time. It had to be this way. And it's glorious. What a time to be alive.
0:33

Translation: I Donald Trump have made moves and signed orders so that we can put the government on pause. During this period, we will run a multi layered psyop for multiple reasons. Our country was infiltrated. Our citizens were divided and lulled into slavery. To correct these issues, we have written a story and produced a show/cover story. The show will allow the American people to see what we were up against and, in turn, weoponizing the people... all while saving the kids, revamping the financial system, and derooting corruption of every form globally. We are 100% reaching the precipice. It is time. It had to be this way. And it's glorious. What a time to be alive.

Jack Straw

163,577 views • 2 years ago

Translation: I Donald Trump have made moves and signed orders so that we can put the government on pause. During this period, we will run a multi layered psyop for multiple reasons. Our country was infiltrated. Our citizens were divided and lulled into slavery. To correct these issues, we have written a story and produced a show/cover story. The show will allow the American people to see what we were up against and, in turn, weoponizing the people... all while saving the kids, revamping the financial system, and derooting corruption of every form globally. We are 100% reaching the precipice. It is time. It had to be this way. And it's glorious. What a time to be alive.
0:34

Translation: I Donald Trump have made moves and signed orders so that we can put the government on pause. During this period, we will run a multi layered psyop for multiple reasons. Our country was infiltrated. Our citizens were divided and lulled into slavery. To correct these issues, we have written a story and produced a show/cover story. The show will allow the American people to see what we were up against and, in turn, weoponizing the people... all while saving the kids, revamping the financial system, and derooting corruption of every form globally. We are 100% reaching the precipice. It is time. It had to be this way. And it's glorious. What a time to be alive.

Joe Rambo

39,611,712 views • 3 years ago

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.
2:41

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,032 views • 5 months ago

Check out our #ICRA2024 paper "Actor-Critic Model Predictive Control." Model-free #reinforcementlearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) benefits from robustness and online replanning capabilities. We combine both approaches by introducing a new framework called Actor-Critic Model Predictive Control. The key idea is to embed a differentiable MPC within an Actor-Critic RL framework. The proposed approach leverages the short-term predictive optimization capabilities of MPC with the exploratory and end-to-end training properties of RL. The resulting policy effectively manages both short-term decisions through the MPC-based actor and long-term prediction via the critic network, unifying the benefits of both model-based control and end-to-end learning. We validate our method in simulation and the real world with a quadcopter across various high-level tasks. We show that the proposed architecture can achieve real-time control performance, learn complex behaviors via trial and error, and retain the predictive properties of the MPC to better handle out-of-distribution behavior. Paper: Full Video with more details: Kudos to Ángel Romero, Yunlong Song IEEE ICRA University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)
1:26

Check out our #ICRA2024 paper "Actor-Critic Model Predictive Control." Model-free #reinforcementlearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) benefits from robustness and online replanning capabilities. We combine both approaches by introducing a new framework called Actor-Critic Model Predictive Control. The key idea is to embed a differentiable MPC within an Actor-Critic RL framework. The proposed approach leverages the short-term predictive optimization capabilities of MPC with the exploratory and end-to-end training properties of RL. The resulting policy effectively manages both short-term decisions through the MPC-based actor and long-term prediction via the critic network, unifying the benefits of both model-based control and end-to-end learning. We validate our method in simulation and the real world with a quadcopter across various high-level tasks. We show that the proposed architecture can achieve real-time control performance, learn complex behaviors via trial and error, and retain the predictive properties of the MPC to better handle out-of-distribution behavior. Paper: Full Video with more details: Kudos to Ángel Romero, Yunlong Song IEEE ICRA University of Zurich UZH Science UZH Space Hub Aerial Core AUTOASSESS European Research Council (ERC)

Davide Scaramuzza

34,889 views • 2 years ago

We are excited to share our latest work, "Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning," done in collaboration with Google DeepMind . Autonomous drones have reached superhuman speed in isolation, but what happens when multiple agents share the same airspace? Paper: Website: Video: Using league-based self-play, we train #ReinforcementLearning agents that race against a diverse, evolving population of opponents. Through this competitive training, sophisticated behaviors emerge without explicit programming: strategic overtaking, proactive collision avoidance, and even awareness of aerodynamic downwash from nearby drones. In real-world multi-player races at speeds exceeding 80kph (50 mph) and accelerations up to 7g, our agents outperform a five-time Swiss national drone racing champion while reducing collision rates by 50% compared to single-agent baselines. Crucially, training against diverse artificial opponents enables zero-shot generalization to human pilots, achieving over 90% race completion in mixed human-AI races with up to four competitors. A key insight: human pilots adopt riskier strategies when trailing, leading to more crashes under competitive pressure. Our learned policies, by contrast, maintain consistent safety margins regardless of race standing, a property essential for deploying autonomous systems alongside humans. Also, the multi-agent self-play policies are more robust than those trained independently, suggesting that training in competitive environments is not only key to winning races but also to learning safer, more reliable autonomy for real-world multi-robot systems. Kudos to Ismail Geles, Leonard Bauersfeld, Markus Wulfmeier! Ismail Geles Leonard Bauersfeld Markus Wulfmeier European Research Council (ERC) UZH IfI University of Zurich UZH Science UZH Space Hub Swiss Robotics NCCR Robotics
1:47

We are excited to share our latest work, "Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning," done in collaboration with Google DeepMind . Autonomous drones have reached superhuman speed in isolation, but what happens when multiple agents share the same airspace? Paper: Website: Video: Using league-based self-play, we train #ReinforcementLearning agents that race against a diverse, evolving population of opponents. Through this competitive training, sophisticated behaviors emerge without explicit programming: strategic overtaking, proactive collision avoidance, and even awareness of aerodynamic downwash from nearby drones. In real-world multi-player races at speeds exceeding 80kph (50 mph) and accelerations up to 7g, our agents outperform a five-time Swiss national drone racing champion while reducing collision rates by 50% compared to single-agent baselines. Crucially, training against diverse artificial opponents enables zero-shot generalization to human pilots, achieving over 90% race completion in mixed human-AI races with up to four competitors. A key insight: human pilots adopt riskier strategies when trailing, leading to more crashes under competitive pressure. Our learned policies, by contrast, maintain consistent safety margins regardless of race standing, a property essential for deploying autonomous systems alongside humans. Also, the multi-agent self-play policies are more robust than those trained independently, suggesting that training in competitive environments is not only key to winning races but also to learning safer, more reliable autonomy for real-world multi-robot systems. Kudos to Ismail Geles, Leonard Bauersfeld, Markus Wulfmeier! Ismail Geles Leonard Bauersfeld Markus Wulfmeier European Research Council (ERC) UZH IfI University of Zurich UZH Science UZH Space Hub Swiss Robotics NCCR Robotics

Davide Scaramuzza

14,519 views • 1 month ago

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!
2:01

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!

Andrew Ng

63,773 views • 6 months ago

🌍Are LLMs aware of cultural and legal safety in today’s geo-diverse world? 🚀Introducing SafeWorld, our #NeurIPS2024 paper and benchmark assessing LLMs’ understanding of geo-diverse safety, based on cultural norms and policies across 50 countries and 493 regions/races. ⚖️We also propose a multi-dimensional framework for evaluating contextual appropriateness, accuracy, and comprehensiveness, revealing major gaps in current LLMs. 🧨To address this, we train SafeWorldLM using DPO, achieving SOTA performance and a 20% higher global human evaluator rating in helpfulness and harmfulness over competing models, including GPT-4o. 🔗Paper: 💻 GitHub: 🫶🏻This is a joint leading effort with Da Yin. Also many thanks to the amazing team Kung-Hsiang Steeve Huang Kai-Wei Chang, and Violet Peng for their hard work. Check out more details and results we conclude from our paper in the thread below. 🧵
1:01

🌍Are LLMs aware of cultural and legal safety in today’s geo-diverse world? 🚀Introducing SafeWorld, our #NeurIPS2024 paper and benchmark assessing LLMs’ understanding of geo-diverse safety, based on cultural norms and policies across 50 countries and 493 regions/races. ⚖️We also propose a multi-dimensional framework for evaluating contextual appropriateness, accuracy, and comprehensiveness, revealing major gaps in current LLMs. 🧨To address this, we train SafeWorldLM using DPO, achieving SOTA performance and a 20% higher global human evaluator rating in helpfulness and harmfulness over competing models, including GPT-4o. 🔗Paper: 💻 GitHub: 🫶🏻This is a joint leading effort with Da Yin. Also many thanks to the amazing team Kung-Hsiang Steeve Huang Kai-Wei Chang, and Violet Peng for their hard work. Check out more details and results we conclude from our paper in the thread below. 🧵

Haoyi Qiu

16,344 views • 1 year ago

Jindal Stainless is excited to announce the launch of our Employee Value Proposition. At Jindal Stainless, we are proud to foster a culture where individuals grow into teams, ideas turn into action, and every role is a stepping stone to something bigger. ​ Embodying our five pillars, learning opportunities, nurturing leaders, exposure to the stainless steel industry, a sense of community, and freedom to experiment, the aim is to bring to life a culture that believes in inclusivity, where every individual is empowered to contribute and lead. Rooted in collaboration, purpose, trust, opportunity, and care, our aim and commitment is to create an environment where people don't just work, they thrive, innovate, and grow together. ​ Be a part of our journey as we shape the future, and write the next chapter with us, where your passion and talent become the catalysts for innovation and excellence. Explore more: #BeTheForce #JindalStainless
3:57

Jindal Stainless is excited to announce the launch of our Employee Value Proposition. At Jindal Stainless, we are proud to foster a culture where individuals grow into teams, ideas turn into action, and every role is a stepping stone to something bigger. ​ Embodying our five pillars, learning opportunities, nurturing leaders, exposure to the stainless steel industry, a sense of community, and freedom to experiment, the aim is to bring to life a culture that believes in inclusivity, where every individual is empowered to contribute and lead. Rooted in collaboration, purpose, trust, opportunity, and care, our aim and commitment is to create an environment where people don't just work, they thrive, innovate, and grow together. ​ Be a part of our journey as we shape the future, and write the next chapter with us, where your passion and talent become the catalysts for innovation and excellence. Explore more: #BeTheForce #JindalStainless

Jindal Stainless

60,403 views • 1 year ago

Here we go again 🚀! Excited to announce that we're building A1Zap (YC W25) with Pennie Li and that we're in the Y Combinator W25 batch in San Francisco! What is A1Base? A1Base gives AI Agents a real world identity for work. We do that by rebuilding Twilio and Okta from the ground up, putting AI Agents first. This means developers can make AI-first agentic applications 10x easier with our API's. ⁉️ Why are we doing this? Because there's a huge torrent of new valuable companies possible with AI agents, but to get their AI Agents to users, they have to chain custom apps, chat interfaces, awkward Slack integrations, browser bots, and wrestle with Twilio’s legacy API (which is built for marketing). We solve this by providing developers with an easy to use API to interface your AI agent with humans/coworkers/users where they are in this case in Whatsapp, Slack, Teams, SMS and more) - with AI Agent features built in. These digital workers are poised to transform how we work and we're the critical infrastructure to help them interact naturally in human workflows. We're not just building another AI tool. We're creating the infrastructure that will enable AI agents to become a natural part of the workforce - handling everything from customer support to sales development to creative work. We're backed by Y Combinator and working with founding teams who share our vision. We believe that in the near future, AI Agents with human coworkers will enable us to pursue more creative and impactful work. Our mission is to help developers build AI Agents that people can partner with and rely on as trusted allies—always with a human-first mindset. If you're thinking about the Agentic future of your company reach out! If you're looking to build your first AI Agentic company - reach out too - we have some amazing open source templates to get you started on the journey. Excited to share more of what we're up to soon 🔜.
1:52

Here we go again 🚀! Excited to announce that we're building A1Zap (YC W25) with Pennie Li and that we're in the Y Combinator W25 batch in San Francisco! What is A1Base? A1Base gives AI Agents a real world identity for work. We do that by rebuilding Twilio and Okta from the ground up, putting AI Agents first. This means developers can make AI-first agentic applications 10x easier with our API's. ⁉️ Why are we doing this? Because there's a huge torrent of new valuable companies possible with AI agents, but to get their AI Agents to users, they have to chain custom apps, chat interfaces, awkward Slack integrations, browser bots, and wrestle with Twilio’s legacy API (which is built for marketing). We solve this by providing developers with an easy to use API to interface your AI agent with humans/coworkers/users where they are in this case in Whatsapp, Slack, Teams, SMS and more) - with AI Agent features built in. These digital workers are poised to transform how we work and we're the critical infrastructure to help them interact naturally in human workflows. We're not just building another AI tool. We're creating the infrastructure that will enable AI agents to become a natural part of the workforce - handling everything from customer support to sales development to creative work. We're backed by Y Combinator and working with founding teams who share our vision. We believe that in the near future, AI Agents with human coworkers will enable us to pursue more creative and impactful work. Our mission is to help developers build AI Agents that people can partner with and rely on as trusted allies—always with a human-first mindset. If you're thinking about the Agentic future of your company reach out! If you're looking to build your first AI Agentic company - reach out too - we have some amazing open source templates to get you started on the journey. Excited to share more of what we're up to soon 🔜.

Pasha Rayan

53,904 views • 1 year ago

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:
2:34

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:

Andrew Ng

886,105 views • 9 months ago

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:
2:41

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

Andrew Ng

86,457 views • 1 year ago