arXiv cs.CL· Dean Light, Michael Theologitis, Kshitish Ghate, Shuyue Stella Li, Benjamin Newman, Chirag Shah, Aylin Caliskan, Pang Wei Koh, Dan Suciu, Yulia Tsvetkov·· 13 小时前AI 评分55
Deep Reasoning：用结构化元推理为通用智能体动态构建推理脚手架
Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
AI 导读
论文提出 Deep Reasoning，一种在推理时通过结构化元推理为任务构建专属脚手架的方法，并用形式语言把元推理表示为对联想推理、形式计算和递归子问题求解的可执行分解。
正文 · 原文
Abstract:Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance. These scaffolds are effective when their prescribed structure matches the task, but brittle when solving the task requires adapting the structure of reasoning itself. We introduce Deep Reasoning -- an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning. Deep Reasoning uses a formal language that represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving, enabling decomposition principles to be encoded as in-context examples that guide test-time scaffold construction. We instantiate this approach in a general-purpose agent (DOLORES) that distributes complex tasks across more controlled reasoning threads. We evaluate it against state-of-the-art scaffolding methods across four hard benchmarks: multi-hop reasoning, long-chain question answering, long-context aggregation, and deep research-style information seeking. DOLORES outperforms all evaluated scaffolds across three model sizes and two model families, improving over the strongest evaluated scaffold baseline by 24.8% on average. DOLORES distributes cognition across structured, lower-load reasoning threads, thereby reducing premature termination and hallucinations. This advantage can even bridge the scaling gap, with an 8B version surpassing all evaluated 32B baselines from the same family in more than half the settings. These results point toward future agentic systems that treat scaffolding as adaptive reasoning, constructing the structure each task requires just-in-time.
| Comments: | Accepted to Neurips 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.11388 [cs.CL] |
| (or arXiv:2605.11388v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11388 arXiv-issued DOI via DataCite |
Submission history
From: Dean Light [view email]
[v1]
Tue, 12 May 2026 01:21:37 UTC (2,968 KB)
[v2]
Wed, 21 Oct 2026 02:42:02 UTC (752 KB)
来源：arXiv cs.CL · arxiv.org