Shannon Shen's banner

Shannon Shen

@shannonzshen • 2,716 subscribers

PhD Student @MIT_CSAIL | previously @allen_ai @semanticscholar @harvard @brownuniversity

Shorts

We share our early research on building Software World - a "GitHub" run by agents. We deploy agents for Python packages in a dependency chain, and each agent is tasked with collaborating with others and optimizing the package it owns.

We share our early research on building Software World - a "GitHub" run by agents. We deploy agents for Python packages in a dependency chain, and each agent is tasked with collaborating with others and optimizing the package it owns.

39,458 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

CLM is one of the most elegant ideas we've worked on together. To me, it starts with a simple interaction need: there are many cases where I just want the agent to make surgical edits to the context. For example, when the agent finishes one task and prepares for another, it should ideally be able to clean up the context for the next one, just as a human would. And there are many such cases! Instead of hard-coding such rules into the harness (I doubt that's even possible), what would a first-principles solution to this problem look like? It turns out to be shockingly simple: ask the LLM to manage the context itself! Not only can this help the agent more efficiently solve the next task, but it can also be applied recursively to many more complex cases. This unlocks new agent capabilities across a variety of challenging, long-running, and open-ended tasks. For example, equipped with CLM, the agents can run continuously for hours on challenging tasks like EdgeBench or our new software world repository optimization tasks, and achieve really good results. Check out the CLM paper for more method details and many other cool results!

CLM is one of the most elegant ideas we've worked on together. To me, it starts with a simple interaction need: there are many cases where I just want the agent to make surgical edits to the context. For example, when the agent finishes one task and prepares for another, it should ideally be able to clean up the context for the next one, just as a human would. And there are many such cases! Instead of hard-coding such rules into the harness (I doubt that's even possible), what would a first-principles solution to this problem look like? It turns out to be shockingly simple: ask the LLM to manage the context itself! Not only can this help the agent more efficiently solve the next task, but it can also be applied recursively to many more complex cases. This unlocks new agent capabilities across a variety of challenging, long-running, and open-ended tasks. For example, equipped with CLM, the agents can run continuously for hours on challenging tasks like EdgeBench or our new software world repository optimization tasks, and achieve really good results. Check out the CLM paper for more method details and many other cool results!

15,739 views • 12 days ago

Super excited to share our open interactive demo for DR Tulu-8B! It supports web and literature search with full transparency — you can see the model's thinking traces and tool outputs as it reasons through your query. 🔗 📝

Super excited to share our open interactive demo for DR Tulu-8B! It supports web and literature search with full transparency — you can see the model's thinking traces and tool outputs as it reasons through your query. 🔗 📝

28,021 views • 8 months ago

No more content to load