[HN Gopher] Solving a million-step LLM task with zero errors
       ___________________________________________________________________
        
       Solving a million-step LLM task with zero errors
        
       Author : Anon84
       Score  : 107 points
       Date   : 2025-11-18 16:26 UTC (6 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | LMKIIW wrote:
       | I dunno, even though the authors address its use, making the task
       | Tower of Hanoi doesn't meet the excitement of the title.
        
         | NitpickLawyer wrote:
         | And yet the reverse paper was posted ad nauseam, covered by
         | every news slop site, and overblown with really negative takes.
        
         | charcircuit wrote:
         | Especially since it's a recursive problem so each step is
         | naturally broken up into subtasks. And the algorithm of what
         | subtasks to break it up in to is public. This makes it much
         | easier for it to get down to a case that the LLM can reliable
         | solve.
        
       | cs702 wrote:
       | Nice!
       | 
       | Briefly, the idea is recursively to decompose tasks into the
       | simplest possible steps, recursively call (relatively small) LLMs
       | as agents to execute one step at a time, and using a clever
       | voting scheme to choose how to execute each step. The authors use
       | this technique to get a relatively small LLM to solve Towers of
       | Hanoi with 20 rings (1M steps). All of it using natural language.
       | 
       | The most obvious question is whether other tasks, more
       | interesting -- less "rote" -- than Towers of Hanoi, can similarly
       | be recursively decomposed into simple steps. I'm not sure that's
       | always possible.
        
         | adastra22 wrote:
         | Why not? That's basically how NASA manages large projects.
        
           | mulmen wrote:
           | NASA has done a lot of amazing things but I wouldn't bet on
           | them winning a Super Bowl.
        
             | HarHarVeryFunny wrote:
             | They'd have a 50% chance of winning one on Mars, since it
             | would just be NASA vs China
        
               | bangaladore wrote:
               | Every year NASA has a 50% chance of winning the
               | Superbowl- even on Earth!
               | 
               | Either they win or don't. /s
        
           | Julien_r2 wrote:
           | I could imagine that even a small task at NASA might involve
           | more knowledge and logic than the smallest task for a Hanoi's
           | tower problem.
           | 
           | Depends on what is considered as small enough for the LLM to
           | be resolved with a high confidence.
        
           | Uehreka wrote:
           | One issue I often run into with this stuff is the tightly
           | coupled nature of things in the real world. I'll fashion an
           | example:
           | 
           | Let's say you break a job down into 3 tasks: A, B and C.
           | Doing one of those tasks is too much for an LLM to accomplish
           | in one turn (this is something you learn intuitively through
           | experience), but an LLM _could_ break each task into 3
           | subtasks. So you do that, and start by having the LLM break
           | task A into subtasks A1, A2 and A3. And B into B1, B2 and B3.
           | But when you break down task C, the LLM (which needs to start
           | with a fresh context each time since each "breakdown" uses
           | 60-70% of the context) doesn't know the details of task A,
           | and thus writes a prompt for C1 that is incompatible with
           | "the world where A1 has been completed".
           | 
           | This sort of "tunnel vision" is currently an issue with
           | scaling 2025 agents. As useful context lengths get longer
           | it'll get easier, but figuring out how to pack exactly the
           | right info into a context is tough, especially when the tool
           | you'd reach for to automate it (LLMs) are the same tool that
           | suffers from these context limitations.
           | 
           | None of this means big things aren't possible, just that the
           | fussyness of these systems increases with the size of the
           | task, and that fussyness leads to more requirements of "human
           | review" in the process.
        
           | etamponi wrote:
           | "basically" is doing a lot of work in this sentence.
        
           | pinkmuffinere wrote:
           | Reasoning by analogy is great for intuition, but doesn't
           | guarantee real results hold. Consider "voltage is like water
           | pressure in pipes, so if there's a cut in my wire's
           | insulation, the device won't get enough voltage" -- clearly
           | this is not true, even though it relies on an analogy that's
           | generally useful.
        
             | alwa wrote:
             | I really like that analogy, thank you for it. Also applies
             | to "it's overvoltage, so I just need to poke a little hole
             | in it to let the excess bleed out"...
        
               | wat10000 wrote:
               | That one can work, briefly, depending on how conductive
               | your tool is.
        
             | CamperBob2 wrote:
             | Well, corona losses are a thing, after all.
        
           | th0ma5 wrote:
           | This is a really good analogy because the complex
           | intersections between multiple groups independently working
           | and trying to collaborate together into a collaborative
           | hierarchy towards one large goal was one of the things that
           | hid a lot of the problems that led to the Challenger
           | disaster, according to Feynmen.
        
         | naasking wrote:
         | > All of it using natural language.
         | 
         | Combining this with those approaches that recursively reason in
         | latent space would be interesting.
        
         | wordpad wrote:
         | This works because a problem could be broken down to a prompt
         | which rarely hallucinates.
         | 
         | Most real world prompts can't be reduced to something so
         | consistent and reliable.
         | 
         | Their key finding was that the number of votes grows linearly
         | with number of prompts you are trying to chain.
         | 
         | However the issue is that the number of votes you need will
         | grow exponentially with hallucination rate.
        
         | patcon wrote:
         | > into the simplest possible steps, recursively call
         | (relatively small) LLMs as agents to execute one step at a
         | time, and using a clever voting scheme to choose how to execute
         | each step.
         | 
         | It's like humans! Everything old is new again :)
        
         | esafak wrote:
         | It seems like this could be implemented by any harness.
        
       | zer00eyz wrote:
       | On the surface this is an interesting concept...
       | 
       | The paper however, meh...
       | 
       | No mention of MoE. One would think this is a logical evolution of
       | that but not a mention (that I saw). Its own rubric for the task,
       | Towers of Hanoi, was admittedly weak.
       | 
       | LLM papers are starting to look like the last decade of JS
       | frameworks and Tools. Only with less code and more academics, and
       | thats disappointing, because I think a lack of pragmatism and
       | grounding is now holding the field back...
        
       | awei wrote:
       | one issue I see is when steps in a plan depend on one another,
       | when you cannot know all the next steps exactly before seeing the
       | results of the previous ones, when you may have to backtrack
       | sometimes
        
       | htrp wrote:
       | > The approach relies on an extreme decomposition of a task into
       | subtasks, each of which can be tackled by focused microagents.
       | The high level of modularity resulting from the decomposition
       | allows error correction to be applied at each step through an
       | efficient multi-agent voting scheme.
       | 
       | Big if that the decomposition and the voting happen accurately
       | for anything other than toy problems
        
         | yorwba wrote:
         | The approach in the paper specifically addresses the case where
         | an LLM can usually solve a task when it requires few steps, but
         | fails for the same kind of task with more steps because it
         | randomly gets a step in the middle wrong and then derails. It
         | can't do anything for tasks that the LLM can't solve even when
         | there's just a few steps.
         | 
         | In other words, it compensates for random error, not systematic
         | error.
        
       | andai wrote:
       | I have ADHD and the same approach works for me. (In fact, most
       | days it is essential!)
        
         | binary132 wrote:
         | do you have an algorithm for breaking down, organizing, and
         | scheduling the small tasks, though? can it also be broken down?
        
       | andai wrote:
       | Worth opening the pdf just for the graph on page 1.
        
         | mNovak wrote:
         | Really seems like the reason logarithmic scales were invented..
        
         | arscan wrote:
         | In case you want to know what's going on in the left side of
         | that chart, they gave a log scale in appendix a. I was thinking
         | it was silly to not just use that version on the top, but I
         | guess log scales make big differences 'feel' smaller.
        
           | kevmo314 wrote:
           | At that rate, they might as well have gone one step further
           | and made the x axis exponential scale to make it feel _even
           | bigger_.
        
         | esafak wrote:
         | A striking example of how not to present data. If the Cognizant
         | AI team is here: please can you fix it in the next version of
         | the paper?
        
           | rdlw wrote:
           | I think it's a brilliant example of how to use data to make a
           | point.
           | 
           | https://xkcd.com/1162/
        
             | jmpeax wrote:
             | Except on figure 1 they're all at 0, making it look like
             | the authors didn't know how to use the models or
             | deliberately made them do nothing.
        
           | datadrivenangel wrote:
           | http://www.vibechart.net
        
       | mattpk wrote:
       | Here is the pseudocode of MAKER:                 state =
       | init_state()       while state is not complete:         state =
       | LLM("You are a helpful assistant. The rules and format of the
       | game is [...]. The correct strategy to use at each step is [...].
       | The current state is [...]. Output the state after making the
       | next move")
        
       | vatsachak wrote:
       | And you can decompose the proof of Fermat's last theorem into
       | logical combinators.
       | 
       | The meat is in decomposing the difficult problem into steps
        
       | sublimefire wrote:
       | The problem is how to even define a task using the English
       | language and make sure there is enough entropy to infer the
       | detailed intent. For it to be later split into zillions of small
       | steps which can be executed over time by an LLM.
        
       | lubujackson wrote:
       | This has seemed to me to be the natural next step to turn LLMs
       | into more deterministic tools. Pushing the frontier is nice, but
       | I think LLMs have a whole different gear when they are able to
       | self-decompose in a reliable way. Most of my success creating
       | reusable LLM products came from determining where
       | requirements/outputs need to be "hard" vs. "soft".
        
       ___________________________________________________________________
       (page generated 2025-11-18 23:00 UTC)