Recursive Language Models · HackerPapers discussions

Recursive Language Models — mentioned by killerstorm

Thu, 01 Oct 2026 23:02:02 GMT

Related: "Recursive Language Models" https://arxiv.org/abs/2512.24601

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by andai

Thu, 30 Jul 2026 19:36:58 GMT

I think this is an unsolved problem. The most interesting thing I saw here is the Recursive Language Models paper. https://arxiv.org/abs/2512.24601 There's also a great write up here by the author: https://alexzhang13.github.io/blog/2025/rlm/

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by andai

Wed, 24 Jun 2026 02:02:04 GMT

Very interesting. Haven't heard of RLMs before. https://github.com/alexzhang13/rlm > We propose Recursive Language Models (RLMs), a general inference paradigm that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. > We find that RLMs can successfully process inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of vanilla frontier LLMs and common long-context and coding scaffolds [...] across…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by ihrimech

Mon, 27 Apr 2026 10:18:33 GMT

Extract of the study : We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference paradigm that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs can successfully process inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of vanilla frontier…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by bob1029

Sat, 14 Mar 2026 14:58:01 GMT

It's almost certainly not quadratic at 1M. This would be wildly infeasible at scale. 10^6^2 = 10^12. That's a trillion things. They are probably doing something like putting the original user prompt into the model's environment and providing special tools to the model, along with iterative execution, to fully process the entire context over multiple invokes. I think the Recursive Language Model paper has a very good take on how this might go. I've seen really good outcomes in my local experimentation around this concept: https://arxiv.org/abs/2512.24601 You can get exponential scaling with…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by jameslk

Fri, 20 Feb 2026 22:33:09 GMT

> Certainly interesting for very low latency applications which need < 10k tokens context. I’m really curious if context will really matter if using methods like Recursive Language Models[0]. That method is suited to break down a huge amount of context into smaller subagents recursively, each working on a symbolic subset of the prompt. The challenge with RLM seemed like it burned through a ton of tokens to trade for more accuracy. If tokens are cheap, RLM seems like it could be beneficial here to provide much more accuracy over large contexts despite what the underlying model can handle 0.…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by cs702

Mon, 16 Feb 2026 15:59:05 GMT

> By 50,000 tokens, your conversation’s costs are probably being dominated by cache reads. Yeah, it's a well-known problem. Every AI company is working on ways to deal with it, one way or another, with clever data center design, and/or clever hardware and software engineering, and/or with clever algorithmic improvements, and/or with clever "agentic recursive LLM" workflows. Anything that actually works is treated like a priceless trade secret. Nothing that can put competitors at a disadvantage will get published any time soon. There are academics who have been working on it too, most notably…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — HN submission

Wed, 11 Feb 2026 13:10:23 GMT

Show HN: CodeRLM – Tree-sitter-backed code indexing for LLM agents

I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking every street. You'll eventually build a mental map, but claude never does - at least not any that persists across different contexts. The Recursive Language Models paper from Zhang, Kraska, and Khattab at MIT CSAIL introduced a cleaner framing. Instead of cramming everything into…

81 points; 37 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Recursive Language Models — mentioned by bob1029

Fri, 23 Jan 2026 09:41:25 GMT

https://arxiv.org/abs/2512.24601

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — HN submission

Wed, 21 Jan 2026 21:24:28 GMT

Show HN: Infinate –O(k)constant-time spatial attention for unlimited LLM context

I built infinate, an open-source (Apache 2.0) attention mechanism that places tokens in a 3D semantic space and limits attention to ~50 nearest neighbors via exponential decay + hard cutoff. This gives true O(k) constant complexity: latency ~7–14 ms and memory fixed (1.50 MB in production) even at 10M+ tokens on CPU. Latest update (Jan 20, 2026): Milestone 1.11 – Strafe Jumping Navigation. As a longtime Quake player, I applied real game physics exploits (7/9 validated) — bunny hop, circle jump, warp lanes, momentum accumulation, LOD hopping, etc. — to make semantic traversal ultra-fast, like…

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Recursive Language Models — HN submission

Wed, 21 Jan 2026 17:49:54 GMT

Show HN: RLM-MCP optimize context in Claude Code Using MIT's recursive LM paper

RLM-MCP – Analyze massive files in Claude Code using MIT's Recursive Language Models. I built an MCP server that lets Claude Code analyze files that exceed its context window by implementing the Recursive Language Models approach from MIT (arXiv:2512.24601). The problem: Claude Code can't fit a 10GB log file in its context. Traditional grep/read returns thousands of tokens of raw matches. The solution: Instead of stuffing data into context, treat the file as an external environment. Claude writes Python code, the MCP server executes it on the full file, and only the results come back. You…

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Recursive Language Models — mentioned by zendizmo

Tue, 20 Jan 2026 01:03:32 GMT

Hi HN, I built RLM Analyzer, an open-source tool for analyzing codebases using Recursive Language Models. Problem: LLMs have context limits. Large codebases don't fit. Solution: Based on MIT CSAIL's RLM paper (arXiv:2512.24601), the AI writes code to explore files and delegates analysis to sub-LLMs. Key innovations: - Context compression (50-70% token savings) - Sliding window history - Memory bank for key findings - Adaptive compression based on usage Example commands: rlm summary # Codebase overview rlm security # Vulnerability scan rlm arch # Architecture analysis rlm ask "How does auth…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by westurner

Sat, 17 Jan 2026 23:50:59 GMT

ScholarlyArticle: "Recursive Language Models" (2025) https://arxiv.org/abs/2512.24601 /? recursive language models: https://hn.algolia.com/?q=Recursive+Language+Models : - https://news.ycombinator.com/item?id=45596059 - https://news.ycombinator.com/item?id=46475395

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by bob1029

Sun, 11 Jan 2026 18:57:35 GMT

Building some prototypes around the Recursive Language Model paper. I'm currently working on integrating it with Unity for scene and script automation. Thinking about standardized patterns for retrofitting this into other existing business systems. If I can make it drive Unity reasonably well, I think it could drive a lot of things. https://arxiv.org/abs/2512.24601

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by bob1029

Mon, 05 Jan 2026 20:52:57 GMT

> you have a massive pile of text, and you need to split it into smaller pieces that fit into embedding models or context windows. I think the recently posted Recursive Language Models paper approaches this in a far more compelling way. They put the long context into the environment and make the LLM write and iterate python code to query against it in a recursive loop. Fig. 2 & 4 are most relevant here. https://news.ycombinator.com/item?id=46475395 https://arxiv.org/abs/2512.24601 I really like this because it is in The Bitter Lesson genre of solutions. Make the model learn the best way to…

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — mentioned by larodi

Sun, 04 Jan 2026 11:05:27 GMT

Alex Zhang just published the repo alongside already published paper here https://arxiv.org/abs/2512.24601v1

Paper and discussion history. A mention is not an endorsement.

Recursive Language Models — HN submission

Sat, 03 Jan 2026 11:29:33 GMT

Recursive Language Models

161 points; 23 discussion replies on HN. Paper and source history. A submission is not an endorsement.