Clip / AI Agents

A 9B model as an RLM beating frontier models on long reasoning

From Recursive Coding Agents - Raymond Weitekamp, OpenProse · ≈5:57

Benchmark claim on Long CoT, whose problems are hard because reasoning chains exceed what any model can hold — recursion plus code lets a laptop-sized model outperform frontier models used as plain LLMs.

What’s in it

Benchmark claim on Long CoT, whose problems are hard because reasoning chains exceed what any model can hold — recursion plus code lets a laptop-sized model outperform frontier models used as plain LLMs.

Watch this moment ↗

Clip transcript

amazing results uh using it as memory. I was also able to show state-of-the-art results where the RLM framework and specifically the DSPy implementation of it was able to get state-of-the-art uh results on long reasoning tasks. Now, there's this new benchmark Long CoT. I won't go into the details in depth, but the idea of this benchmark was that the problems are hard specifically because they require so many um steps of reasoning uh in in the like analysis sequence or the chain of thought um that most uh reasoning models, including the top ones, can't hold the thread for long enough. Um if you allow the uh RLM to solve the problem uh using a combination of code and recursive calls to sub agents, then a very small model, Qwen 3.59B, you could run this on a laptop, uh can actually beat So, Qwen 3.59B as an RLM can beat Opus and um and GPT-5.4, all the top frontier models as LLMs on these long reasoning tasks. So, they're extremely extremely powerful.

Intel