LCM: Lossless Context Management [pdf]
papers.voltropy.com
LCM: Lossless Context Management [pdf]
1–10 of 32 posts
Re: LCM: Lossless Context Management [pdf]
#2Hi, I'm Clint, one of the co-authors of this paper.
I'd like to quickly summarize what is different about our approach and why it matters.
Our work was inspired by brilliant research done at MIT CSAIL on "Recursive Language Models" (RLMs). One of the controversies has been whether these models are just a formalization of what agents like Claude Code already do vs. whether they bring new capabilities to the table.
By outperforming Claude on the major long-context benchmark, we provide a strong signal that something fundamentally new is happening. (In other words, it's not "just Claude Code" because it demonstrably outperforms Claude Code in the long-context regime.)
Where our contribution, LCM, differs from RLMs is how we handle recursion. RLMs use "symbolic recursion" -- i.e., they have an LLM write a script to recursively call itself in order to manipulate the context, which is stored in a REPL. This provides maximum flexibility... but it often goes wrong, since the LLM may write imperfect scripts.
LCM attempts to decompose the recursion from RLMs into deterministic primitives so that the control flow can be managed by an engine rather than left to the whims of the LLM. In practice, this means we replace bespoke scripts with two mechanisms: (1) A DAG-based context management system that works like paged virtual memory, except for managing conversations and files; and (2) Operator-level recursion, like "Map" for LLMs, which lets one tool call process thousands of tasks.
An analogy we draw in the paper is the evolution from GO-TO statements (of Dijkstra's "Considered Harmful" fame) to structured programming. RLMs are maximally expressive, but all of that power comes with the risk of things going awry. We have built a more mechanistic system, which can provide stronger guarantees when deployed in production with today's models.
Happy to answer any questions! Thanks for taking a look at the paper!
Re: LCM: Lossless Context Management [pdf]
#3Hi, I'm Clint, one of the co-authors of this paper. I'd like to quickly summarize what is different about our approach and why it matters. Our work was inspired by brilliant research done at MIT CSAIL on "Recursive Language Models" (RLMs). One of the controversies has been whether these models are just a formalization of what agents like Claude Code already do vs. whether they bring new capabilities to the table. By…
This looks super useful! And it’s intellectually appealing to think that the LLM will have the ability to think back precisely and we can rely on DAG tooling to reason about and keep track of history (and correct history).
Have you considered making an openclaw plugin/PR for it? I understand you have your own coding CLI tool, but I don’t think this looks so hard to implement that it can’t be implemented elsewhere.
Either way, thanks for sharing this.
Re: LCM: Lossless Context Management [pdf]
#4Hi, I'm Clint, one of the co-authors of this paper. I'd like to quickly summarize what is different about our approach and why it matters. Our work was inspired by brilliant research done at MIT CSAIL on "Recursive Language Models" (RLMs). One of the controversies has been whether these models are just a formalization of what agents like Claude Code already do vs. whether they bring new capabilities to the table. By…
Thank you so much for your work!
I've echoed the sentiment here on HN (and elsewhere) that these kinds of mechanisms seem to be a pathway to extending context longer and longer and longer and I wish I could toy around with this technology right now (can I?). I'm so excited!!
Your work is the shoulders-built-on-shoulders upon which other giants shall keep on building. Thank you so much.
Re: LCM: Lossless Context Management [pdf]
#5Hi, I'm Clint, one of the co-authors of this paper. I'd like to quickly summarize what is different about our approach and why it matters. Our work was inspired by brilliant research done at MIT CSAIL on "Recursive Language Models" (RLMs). One of the controversies has been whether these models are just a formalization of what agents like Claude Code already do vs. whether they bring new capabilities to the table. By…
This looks super useful! And it’s intellectually appealing to think that the LLM will have the ability to think back precisely and we can rely on DAG tooling to reason about and keep track of history (and correct history). Have you considered making an openclaw plugin/PR for it? I understand you have your own coding CLI tool, but I don’t think this looks so hard to implement that it can’t be implemented elsewhere. Ei…
Yes, that is actually the next thing we are shipping!
We have heard from a ton of OpenClaw users that the biggest barrier to them getting everything they want out of their agents is that memory is not a solved problem.
LCM could be a great solution to that. Stay tuned -- will ship it ASAP.
Re: LCM: Lossless Context Management [pdf]
#6Hi, I'm Clint, one of the co-authors of this paper. I'd like to quickly summarize what is different about our approach and why it matters. Our work was inspired by brilliant research done at MIT CSAIL on "Recursive Language Models" (RLMs). One of the controversies has been whether these models are just a formalization of what agents like Claude Code already do vs. whether they bring new capabilities to the table. By…
Thank you so much for your work! I've echoed the sentiment here on HN (and elsewhere) that these kinds of mechanisms seem to be a pathway to extending context longer and longer and longer and I wish I could toy around with this technology right now (can I?). I'm so excited!! Your work is the shoulders-built-on-shoulders upon which other giants shall keep on building. Thank you so much.
Thanks for the kind words.
Yes, we think there is a ton of low-hanging fruit from taking lessons from OS/PL theory and applying them to LLM tooling.
This is our first contribution in that direction. There will be more!
Re: LCM: Lossless Context Management [pdf]
#7Earlier quoted context omitted.
This looks super useful! And it’s intellectually appealing to think that the LLM will have the ability to think back precisely and we can rely on DAG tooling to reason about and keep track of history (and correct history). Have you considered making an openclaw plugin/PR for it? I understand you have your own coding CLI tool, but I don’t think this looks so hard to implement that it can’t be implemented elsewhere. Ei…
Yes, that is actually the next thing we are shipping! We have heard from a ton of OpenClaw users that the biggest barrier to them getting everything they want out of their agents is that memory is not a solved problem. LCM could be a great solution to that. Stay tuned -- will ship it ASAP.
Love it. Yes, compaction is a huge pain point in openclaw, and it EATS tokens.
Re: LCM: Lossless Context Management [pdf]
#8Earlier quoted context omitted.
Thank you so much for your work! I've echoed the sentiment here on HN (and elsewhere) that these kinds of mechanisms seem to be a pathway to extending context longer and longer and longer and I wish I could toy around with this technology right now (can I?). I'm so excited!! Your work is the shoulders-built-on-shoulders upon which other giants shall keep on building. Thank you so much.
Thanks for the kind words. Yes, we think there is a ton of low-hanging fruit from taking lessons from OS/PL theory and applying them to LLM tooling. This is our first contribution in that direction. There will be more!
Oh and to be clear YES you can try it!!!
Just bring an API key. :)
github.com/voltropy/volt
Re: LCM: Lossless Context Management [pdf]
#9Earlier quoted context omitted.
This looks super useful! And it’s intellectually appealing to think that the LLM will have the ability to think back precisely and we can rely on DAG tooling to reason about and keep track of history (and correct history). Have you considered making an openclaw plugin/PR for it? I understand you have your own coding CLI tool, but I don’t think this looks so hard to implement that it can’t be implemented elsewhere. Ei…
Yes, that is actually the next thing we are shipping! We have heard from a ton of OpenClaw users that the biggest barrier to them getting everything they want out of their agents is that memory is not a solved problem. LCM could be a great solution to that. Stay tuned -- will ship it ASAP.
Riffing on this a little, there’s a few things that would be useful:
1 - global namespace - for the gateway agent/coordinator - would make inspecting results of subagent tasks much more safe and efficient, and all the benefits of precision across compaction boundaries for the main chat thread. I could see giving the subagents access to it, or just prompting them fresh and storing results in the global memory - probably the second is better.
2 - permissioned memory spaces - stuff that a given subagent should know without giving them global memory access. Then a gateway could mark some stuff ‘available’ as part of prompting.
This would be a super useful set of primitives - from reading the paper, I think you could do this relatively cheaply, maybe a tagging system for branches/nodes in the DAG. openclaw keeps some sort of track of what subagents should have access to already in the form of skills, but I haven’t looked into the actual permissions architecture.
Re: LCM: Lossless Context Management [pdf]
#10Earlier quoted context omitted.
Yes, that is actually the next thing we are shipping! We have heard from a ton of OpenClaw users that the biggest barrier to them getting everything they want out of their agents is that memory is not a solved problem. LCM could be a great solution to that. Stay tuned -- will ship it ASAP.
Riffing on this a little, there’s a few things that would be useful: 1 - global namespace - for the gateway agent/coordinator - would make inspecting results of subagent tasks much more safe and efficient, and all the benefits of precision across compaction boundaries for the main chat thread. I could see giving the subagents access to it, or just prompting them fresh and storing results in the global memory - probab…
Just passed this on to my co-author who is working on the plug-in. Really appreciate the suggestions!
We will probably ship a fairly basic version to start, but I think there are a lot of cool things that can be added.