arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.06413cs.AI
收藏

自回归推理的内在稳定性极限:长视界执行的结构后果

Intrinsic Stability Limits of Autoregressive Reasoning: Structural Consequences for Long-Horizon Execution

Hsien-Jyh Liao

AI总结:

本文研究了自回归推理的内在稳定性限制,发现长视界执行受限于过程级不稳定性,提出结构治理是解决长视界推理问题的关键。

摘要:

大型语言模型(LLMs)展现出显著的推理能力,但其性能在长视界任务中往往急剧下降,表现出系统性崩溃。传统解释主要将其归因于任务复杂性,如组合搜索爆炸或长期信用分配挑战。在本文中,我们主张这些解释是不完整的:即使在线性、非分支任务中没有语义歧义,自回归执行也受内在稳定性限制。我们提出,长视界推理的根本限制来自于自回归生成过程中级别的不稳定性,而非仅仅来自搜索或任务复杂性,将长视界推理重新定义为结构治理的问题。我们推导出定理A,证明单路径自回归推理中的决策优势随着执行长度呈指数衰减,从而对可维持推理链施加根本性的界限。这一结果意味着一个结构后果:稳定的长视界推理需要离散分割,自然诱导图状执行结构,如有向无环图(DAGs)。在合成环境和真实TextWorld任务中的实证研究揭示出与理论预测一致的可观察性能悬崖。我们的发现为长视界推理失败提供了动态视角,并提出了在纯自回归架构下维持长期一致性的新限制。此外,我们指出短视界评估协议可能会掩盖结构不稳定性,表明未来推理系统可能从扩展转向结构治理。

英文摘要:

Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exhibiting systematic breakdown beyond certain scales. Conventional explanations primarily attribute this phenomenon to task complexity, such as combinatorial search explosion or long-term credit assignment challenges. In this work, we argue that these explanations are incomplete: even in linear, unbranched tasks without semantic ambiguity, autoregressive execution is subject to an intrinsic stability limit. We propose that the fundamental constraint on long-horizon reasoning arises from process-level instability in autoregressive generation rather than solely from search or task complexity, reframing long-horizon reasoning as a problem of structural governance. We derive Theorem~A, showing that decision advantage in single-path autoregressive reasoning decays exponentially with execution length, imposing a fundamental bound on maintainable reasoning chains. This result implies a structural consequence: stable long-horizon reasoning requires discrete segmentation, naturally inducing graph-like execution structures such as directed acyclic graphs (DAGs). Empirical studies in both synthetic environments and real TextWorld tasks reveal observable performance cliffs consistent with theoretical predictions. Our findings provide a dynamical perspective on long-horizon reasoning failure and suggest new limitations on maintaining long-term coherence under purely autoregressive architectures. Furthermore, we highlight that short-horizon evaluation protocols may obscure structural instability, indicating a potential shift from scaling toward structured governance in future reasoning systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑