[HN Gopher] Recursive Language Models (RLMs)
       ___________________________________________________________________
        
       Recursive Language Models (RLMs)
        
       Author : talhof8
       Score  : 48 points
       Date   : 2025-10-15 17:43 UTC (5 hours ago)
        
 (HTM) web link (alexzhang13.github.io)
 (TXT) w3m dump (alexzhang13.github.io)
        
       | jgbuddy wrote:
       | This is old news! Agent-loops are not a model architechture
        
         | laughingcurve wrote:
         | Everything old is new again when you are in academia
        
           | hodgehog11 wrote:
           | This feels primarily like an issue with machine learning, at
           | least among mathematical subdisciplines. As new people
           | continue to be drawn into the field, they rarely bother to
           | read what has come even a few years prior (nevermind a few
           | decades prior).
        
         | layer8 wrote:
         | Loops aren't recursion?
        
       | halfmatthalfcat wrote:
       | It broke new ground!
        
       | ayazhan wrote:
       | https://arxiv.org/abs/2510.04871 another recursive based model
        
         | yorwba wrote:
         | It's a completely different kind of recursion for a completely
         | different (non-language) task.
        
       | gdiamos wrote:
       | Recursion is so popular in computing that this term "recursive
       | language model" is heavily overloaded
       | 
       | It was even before the rise of LLMs
       | 
       | The authors may want to consider a more specific name
        
       | quibit wrote:
       | > Lastly, in our experiments we only consider a recursive depth
       | of 1 -- i.e. the root LM can only call LMs, not other RLMs. It is
       | a relatively easy change to allow the REPL environment to call
       | RLMs instead of LMs, but we felt that for most modern "long
       | context" benchmarks, a recursive depth of 1 was sufficient to
       | handle most problems. However, for future work and investigation
       | into RLMs, enabling larger recursive depth will naturally lead to
       | stronger and more interesting systems.
       | 
       | It feels a little disingenuous to call it a Recursive Language
       | Model when the recursive depth of the study was only 1.
        
       | yandie wrote:
       | This isn't just context optimization. Not much different from
       | agent-to-agent workflow IMO.
        
       | cs702 wrote:
       | Briefly, an RLM wraps an existing language model (LM) together
       | with an environment that can dynamically manipulate the prompt
       | that will be fed into the LM.
       | 
       | The authors use as an environment _a Python REPL that itself can
       | call other instances of the LM_. The prompt is programmatically
       | manipulated as a _Python variable_ on the REPL.
       | 
       | The motivation is for the LM to use Python commands, including
       | commands that call other LM instances, to figure out how best to
       | modify the context at inference time.
       | 
       | The results from early testing look impressive at a first glance:
       | An RLM wrapping GPT-5-mini outperforms GPT-5 by a wide margin on
       | long-context tasks, at significant lower cost.
       | 
       | I've added this to my reading list.
        
       | nowittyusername wrote:
       | My existing project is very similar to this with some other
       | goodies. I agree with the author that focus on systems versus
       | LLM's is the proper next move. Orchestrating systems that manage
       | multiple different llms and other scripts together can accomplish
       | a lot more then a simple ping pong type of behavior. Though I
       | suspect most people who work with agentic solutions are already
       | quite aware of this. What most in that space haven't cracked yet
       | is the dynamic self modifying and improving system, that should
       | be the ultimate goal for these types of systems.
        
       ___________________________________________________________________
       (page generated 2025-10-15 23:00 UTC)