AI 与机器学习2025arxiv.org
零错误求解百万步 LLM 任务
Solving a million-step LLM task with zero errors
进阶 · 约 75 分钟读完前置知识：LLM 基础、递归分解、投票/集成方法
导读
论文研究如何让 LLM 在超长步骤任务中实现零错误：通过递归将任务分解为最简单的步骤，用较小的 LLM 作为 agent 逐步执行，并采用巧妙的投票机制选择每一步的执行方式。作者用该方法让较小的 LLM 用自然语言解出 20 层汉诺塔（约 100 万步）。
HN 关注点：HN 读者长期争论 LLM 的可靠性问题——错误率虽低但长链条任务必然失败，这篇论文正面承认并尝试解决该问题，引发关注。
HN 评论精选
这几条评论里：质疑 2 补充 1
质疑解读核心方法，但质疑该技术能否推广到非机械性任务
不错！简言之，思路是递归地把任务分解成最简单的步骤，递归调用（相对较小的）LLM 作为 agent 每次执行一步，并用巧妙的投票机制选择每一步的执行方式。作者用这个技术让一个较小的 LLM 解出 20 层汉诺塔（100 万步），全程用自然语言。最明显的问题是：比汉诺塔更有趣、不那么机械的任务，是否也能这样递归分解？我不确定这总是可行的。
cs702查看英文原文
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.
补充赞赏论文承认长链条可靠性问题，但质疑为何不用混合符号系统
看到这个明显的问题被正面承认真是令人欣慰：如果任务要求每一步都正确，错误率哪怕只有千分之一，在需要连续执行数千步的任务中也必然失败。我在 HN 的推理辩论中不知多少次因这个话题被围攻，也见过很多论文对此避而不谈。下一个自然的问题是：既然已经把问题分解成大量微步骤并投票，为什么不干脆采用混合符号系统？分解本身就暗示问题域中变量可以较干净地分离。论文中的投票似乎是对候选输出（子问题的解）投票；若换成混合符号系统，可以对求解器的候选输入投票，至少能确保输出总是正确的。
robot-wrangler查看英文原文
> However, this result made it clear that the reliability of state-of-the-art LLMs is fundamentally limited: If they need to complete every step correctly in order to solve a task, after a certain number of steps they will almost surely fail as a result of an underlying propensity to make errors, even when the answer should be obvious. While an error rate of 1-in-1,000 seems low, and would be great on a traditional LLM benchmark, on a task that requires successful execution of thousands of steps in a row, such a system results in inevitable failure. What a relief to see an obvious problem actually acknowledged. I can't even guess how many times I've been shouted down about this exact topic in the reasoning debates on HN, or seen papers just kind of glossing over it as if it were a non-issue. The next really natural question is.. if you're committed to decomposing a problem into tons of microsteps and voting.. why aren't we just embracing hybrid symbolic systems? The decomposition step kind of implies you're in a problem domain where variables separate out somewhat cleanly and that this should be doable. As far as I can tell the "voting" discussed in the paper is about candidate outputs, i.e. solutions to subproblems? If you switch to hybrid symbolic systems, then you can vote on candidate inputs to solvers and at least be damned sure that their output is always correct. Also the success of chain-of-code compared with chain-of-thought approaches could actually imply that having no real solver is maybe not the obstacle you'd expect! Maybe you can invent a semiformal logic just in time that appears to be expressive enough to encapsulate the problem domain, and have the LLM emulate a nonexistent solver. If the error rate with this sort of approach is still too high, then at least you know concretely what solver or formal-language you need to implement in order to improve.
质疑质疑用汉诺塔验证的代表性，认为标题夸大
虽说作者解释了用途，但选汉诺塔作为任务，实在配不上标题带来的兴奋感。
LMKIIW查看英文原文
I dunno, even though the authors address its use, making the task Tower of Hanoi doesn't meet the excitement of the title.
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
历次讨论
- 2025Hacker News 讨论帖222 分 · 95 评
同领域还值得读
DeepSeek-R1：通过强化学习激励 LLM 的推理能力
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
研究如何用强化学习激励大语言模型的推理能力，提出 DeepSeek-R1，并探讨 RL 训练对模型推理表现的影响。
AI 与机器学习2025 · 1,351 分 · 1,056 评 · 引用 30进阶 · 约 80 分钟编辑精选1-bit LLM 时代：面向低成本计算的三值参数
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
提出用三值参数 {-1, 0, 1} 替代 LLM 中的浮点权重，即所谓“1-bit LLM”。
AI 与机器学习2024 · 1,040 分 · 447 评 · 引用 19进阶 · 约 45 分钟编辑精选DeepSeek-V3.2：推进开放大语言模型的前沿
DeepSeek-v3.2: Pushing the frontier of open large language models
这是 DeepSeek-V3.2 的技术报告，延续了 DeepSeek 开源权重模型的路线，目标是让开放模型继续逼近甚至追平前沿闭源模型。
AI 与机器学习2025 · 982 分 · 465 评进阶 · 约 90 分钟编辑精选通过自我对弈与通用强化学习掌握国际象棋和将棋（AlphaZero）
Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
DeepMind 的 AlphaZero 论文：用通用强化学习算法（自我博弈 + MCTS + 神经网络），从零开始仅数小时训练便在国际象棋和将棋上击败了世界顶级引擎 Stock…
AI 与机器学习2017 · 539 分 · 270 评 · 引用 13进阶 · 约 90 分钟编辑精选用强化学习发现更快的矩阵乘法算法
Discovering faster matrix multiplication algorithms with reinforcement learning
论文提出 AlphaTensor，用强化学习搜索矩阵乘法算法。
AI 与机器学习2022 · 518 分 · 111 评专业 · 约 90 分钟编辑精选