Loading video...
Video Failed to Load
A 7-million parameter model outperforming models a thousand times its size on tasks like ARC Prize. That's what recursive reasoning unlocks. In this episode of Decoded, YC's Ankit Gupta and Francois Chaubard break down two recent papers on recursive AI models, HRMs and TRMs, that are achieving state-of-the-art results... show more
128,225 views • 6 months ago •via X (Twitter)
29 Comments

Tune in:

@agupta @FrancoisChauba1 7M params is impressive, but recursive reasoning usually trades weights for more steps at inference. are you seeing a wall clock win too, or mostly benchmark gains once you let it think longer?

@agupta @FrancoisChauba1 Paper links: [2506.21734] Hierarchical Reasoning Model [2510.04871] Less is More: Recursive Reasoning with Tiny Networks

@agupta @FrancoisChauba1 Sounds like a fancy way of over fitting on a single thing, rather than anything novel.

@agupta @FrancoisChauba1 Does that mean that the model was better suited for this task because that is all it was trained for? Like, a specific key for a specific lock. Why would you go through the entire bundle of keys then?

@agupta @FrancoisChauba1 Does recursive reasoning at 7M params hold up on messy, ambiguous real-world inputs? ARC is impressive but structured. Enterprise data is chaos.

What is described as the HRM backprop method sounds very much like Truncated Backprop Through Time (BPTT), where backprop is continued, from a certain hidden state, representing an input sequence so far. This was used “back in the day” when we were training RNNs on long sequences.

This is a really important direction. If recursion at inference time can reliably replace raw parameter scaling for certain reasoning regimes, it reframes what “capability” actually means in LLMs. Still curious how well HRM/TRM generalize beyond curated benchmarks like ARC when you hit messy real-world distribution shifts—but the efficiency signal here is hard to ignore.

@agupta @FrancoisChauba1 recursive reasoning only helps

@agupta @FrancoisChauba1 This is the kind of efficiency breakthrough we actually need.

@paulg @agupta @FrancoisChauba1 Small, task focused models outperform large general purpose ones. The frontier of AI is in specialization.

@agupta @FrancoisChauba1 I suppose its Looped Transformer

@agupta @FrancoisChauba1 A 7M parameter model outperforming ones 1000x its size on reasoning benchmarks is the clearest signal yet that scale isn’t the only path. Recursive computation lets small models think harder, not just be bigger. Architecture innovation is back.

the ARC numbers are wild. a 7M param TRM hitting ~45% on ARC-AGI-2 while frontier models with 1000x the weights sit in the single digits is the clearest signal yet that depth of compute at inference matters more than raw parameter count for actual reasoning. feels like the same lesson AlphaZero taught in 2017, just rediscovered for language.

@agupta @FrancoisChauba1 7M params doing ARC is the bigger story than scale laws this week

@agupta @FrancoisChauba1 7M params beating models a thousand times their size on ARC. The pure-scale thesis is aging poorly.

@agupta @FrancoisChauba1 the honest answer is that we're not even close to tapping into the real value of recursive reasoning yet. most papers are still just scratching the surface.

@agupta @FrancoisChauba1 woot woot!

@agupta @FrancoisChauba1 recursion replacing parameter count is the actual claim. the question worth watching is whether TRMs collapse on the same failure mode the giants did. ARC-AGI-3's biggest error bucket was wrong abstraction from training data and recursion alone doesn't obviously fix that one.

@agupta @FrancoisChauba1 @ycombinator that's wild. is it something to do with the way recursive models break down tasks? would love to know more about how they work.

@agupta @FrancoisChauba1 another cool interview by ycomb

@agupta @FrancoisChauba1 This discussion on recursive reasoning highlights a promising path for efficient AI development. It shows how small models can outperform much larger ones on complex tasks.

@agupta @FrancoisChauba1 Hello Y combinator. I have an idea which I am implementing already. How can I share?

@agupta @FrancoisChauba1 Where do recursive models break down today?

@agupta @FrancoisChauba1

@agupta @FrancoisChauba1

@agupta @FrancoisChauba1 Samsung TRM (arXiv:2510.04871), 7M params, hits 45% ARC-AGI-1 via 2-layer latent recursion , same score bracket as GPT-4o at 1000x the parameter count. Iterative z-loops beat transformer pass-throughs on fluid reasoning per FLOP.

@agupta @FrancoisChauba1 so answer wasn't bigger models just thinking longer

@agupta @FrancoisChauba1 YC is jumping on this nonsense train lol 😂

