News for hackers. Stuff that matters.

A comment on Recursive Language Models (RLMs).

Re:Recursive Language Models (RLMs) by ayazhan on Wednesday October 15, 2025 @04:21PM (#45597896)
https://arxiv.org/abs/2510.04871 another recursive based model
[ Parent | on HN ]
Re:Recursive Language Models (RLMs) by yorwba on Wednesday October 15, 2025 @05:21PM (#45598514)
It's a completely different kind of recursion for a completely different (non-language) task.
[ Parent | on HN ]
Re:Recursive Language Models (RLMs) by foolswisdom on Wednesday October 15, 2025 @07:38PM (#45599690)
I actually came here expecting this to be a language model application of that recursive reasoning paper.
[ Parent | on HN ]
Re:Recursive Language Models (RLMs) by d0mine on Thursday October 16, 2025 @02:09PM (#45608744)
> TRM obtains 45% test-accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, higher than most LLMs (e.g., Deepseek R1, o3-mini, Gemini 2.5 Pro) with less than 0.01% of the parameters.
[ Parent | on HN ]