RLMs on top of LLM

[artile]

@parcadei Hi, Marsla, likely you already heard about RLMs. I'm wondering to hear your ideas on that.

Recursive Language Models (RLM) is a new interface for LLMs with cool ideas by
@a1zhang
!

⚠️ LLMs struggle with long prompts → attention overload & lost info
🔄 RLMs inspect, split & call themselves on chunks, then aggregate results
✅ Handles millions of tokens, reduces noise, improves reasoning
💡 System prompt guides recursion
🎯 RLM trajectories can be used for RL training or distillation (OpenEnv+TRL!!)
https://arxiv.org/pdf/2512.24601

some solutions started to pop-up
just wondering you POV on that, thanks mate!