Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LCM: Lossless Context Management [pdf]

papers.voltropy.com

Post reply on HN
Print view View original

11–20 of 32 posts

Re: LCM: Lossless Context Management [pdf]

#11

Post by quotemstr »

ClintEhrlich wrote: post #2

Hi, 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…

Cool. I agree (consistent with your GOTO analogy) that imposing structure on the model (or a human) can constrain the search space and lead to better choosing given a fixed decision budget.

> deterministic primitives

Are agent-map and LLM-map the only two options you've given the model for recursive invocations? No higher-level, er, reduction operators to augment the map primitives?

Re: LCM: Lossless Context Management [pdf]

#12

Post by belisarius222 »

quotemstr wrote: post #11
ClintEhrlich wrote: post #2

Hi, 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…

Cool. I agree (consistent with your GOTO analogy) that imposing structure on the model (or a human) can constrain the search space and lead to better choosing given a fixed decision budget. > deterministic primitives Are agent-map and LLM-map the only two options you've given the model for recursive invocations? No higher-level, er, reduction operators to augment the map primitives?

Hi, I'm the other author on this paper. You've asked a good question. I had originally planned on writing an agentic_reduce operator to complement the agentic_map operator, but the more I thought about it, the more I realized I couldn't come up with a use case for it that wasn't contrived. Instead, having the main agent write scripts that perform aggregations on the result of an agentic_map or llm_map call made a lot more sense.

It's quite possible that's wrong. If so, I would write llm_reduce like this: it would spawn a sub-task for every pair of elements in the list, which would call an LLM with a prompt telling it how to combine the two elements into one. The output type of the reduce operation would need to be the same as the input type, just like in normal map/reduce. This allows for a tree of operations to be performed, where the reduction is run log(n) times, resulting in a single value.

That value should probably be loaded into the LCM database by default, rather than putting it directly into the model's context, to protect the invariant that the model should be able to string together arbitrarily long sequences of maps and reduces without filling up its own context.

I don't think this would be hard to write. It would reuse the same database and parallelism machinery that llm_map and agentic_map use.

Re: LCM: Lossless Context Management [pdf]

#13

Post by belisarius222 »

vessenes wrote: post #9
ClintEhrlich wrote: post #5

Earlier 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…

Did somebody say 'global namespace'? I spent years working on one of those as part of Urbit... In general, I think you're right. Each conversation is an append-only log at the lowest layer, and I see no reason not to expose that fact as a global namespace, as long as permissions are handled gracefully.

Of course getting permissions to work well might be easier said than done, but I like this direction.

Re: LCM: Lossless Context Management [pdf]

#14

Post by quotemstr »

belisarius222 wrote: post #12
quotemstr wrote: post #11

Earlier quoted context omitted.

Cool. I agree (consistent with your GOTO analogy) that imposing structure on the model (or a human) can constrain the search space and lead to better choosing given a fixed decision budget. > deterministic primitives Are agent-map and LLM-map the only two options you've given the model for recursive invocations? No higher-level, er, reduction operators to augment the map primitives?

Hi, I'm the other author on this paper. You've asked a good question. I had originally planned on writing an agentic_reduce operator to complement the agentic_map operator, but the more I thought about it, the more I realized I couldn't come up with a use case for it that wasn't contrived. Instead, having the main agent write scripts that perform aggregations on the result of an agentic_map or llm_map call made a lot…

Cool! It'll be interesting to follow your work. I've been thinking, as well, about quorum and voting systems that might benefit from some structure. The primitives you've described are great for the "do N things one time each" case, but sometimes I (and the AI) want "do one thing N times: pick the best somehow". (I mean, you can express that with map/reduc over small integers or something, but still: different flavor.) You can even bring public choice theory into it.

Re: LCM: Lossless Context Management [pdf]

#16

Post by dworks »

I built an RLM workflow as a coding agent skill: https://github.com/doubleuuser/rlm-workflow

It has two differences:

1. It does not store chat history, reasoning traces etc, only workflow artifacts (requirements, codebase analysis, implementation plan, etc). I frankly do not believe those things are relevant.

2. It is significantly simpler and more lightweight, using only markdown files

Re: LCM: Lossless Context Management [pdf]

#18

Post by ClintEhrlich »

carshodev wrote: post #15

Seems that this would be useful for subagents aswell. You could still allow an agent down the line to inspect the thinking traces/steps of a subagent, by creating a mapping of the content. Thus keeping it compressed but accesible if requested.

Our system uses sub-agents as a core part of its architecture.

That terminology can be confusing, because in other cases (and sometimes in our own architecture, like when executing thousands of operations via MAP) a sub-agent may be a smaller model given less complex individual tasks.

But the core mechanism we use for simulating unlimited context is to allow the main model to spin up instances of itself (sub-agents) with the previously summarized portion of the context expanded into its full, uncompressed state.

Expanding summaries into full text in sub-agents rather than the main thread is a critical part of our architecture, because it prevents the main context window from filling up.

Re: LCM: Lossless Context Management [pdf]

#19

Post by kretaceous »

Re: the lcm_expand(summaryID) tool

> Because expansion can recover arbitrarily large volumes of earlier conversation, this tool is restricted to sub-agents spawned via the Task tool; the main agent cannot call it directly. This restriction prevents uncontrolled context growth in the primary interaction loop.

What if the lcm_expand is called for a summary that has 1000s of messages that immediately floods the sub-agent's own context window?

Does lcm_expand only unroll one "layer" of the DAG and unrolls more if needed by another subagent?

Re: LCM: Lossless Context Management [pdf]

#20

Post by nowittyusername »

Do you have any resources or youtube videos that might also help someone understand the lcm context management a bit better. I think there's something to this, but i'm having trouble wrapping my head around it. i learn well with analogies and im trying to really grok the concept here. If there are other ways you could explain it it would be appreciated. mind you i have built my own agents from scratch so im not a total novice in these areas. my agents already manage context with sub-agents and multi layered conversational histories with RAG thrown in there. But i dont want to make wrong assumptions about your implementations and miss the nuanced important bits. regardless, ill try my best to reread the article and hash it out on my own, thanks for the paper.
Post reply on HN