分析推理模型中的回溯行为，区分有效修正与无效反复。
The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
- 通过回溯动态识别推理过程中的局部修正与重推
- 早期孤立修正多为正确，后期持续聚集的严重回溯常致错误
- 提出基于突发模式的早期退出策略，优于固定长度筛选
推理模型常生成长序列，其中有效自修正与无益反复难以区分。本文通过回溯动态——即长推理序列中的局部重新考虑、撤回或重推——进行研究。在6,000条Qwen3-8B AIME推理轨迹上，标注了段级回溯严重性，并分析事件时间、归一化深度与局部突发结构。结果发现：早期孤立修正通常与正确推理兼容，而错误轨迹更常表现出中至重度回溯，且集中于后期。跨语料库验证显示该定性不对称在其他模型/领域对中同样存在。过滤分析将此信号实例化为前缀因果的早期退出策略：在浅层与中等深度下，基于突发感知的过滤优于仅依赖固定长度的过滤，且仅使用前缀可得特征。中等长度截断仍为完整轨迹强基线，但突发感知控制提供了可部署机制，以区分可恢复修正与潜在不稳定性。
原文摘要 · Abstract (English)
Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction through backtracking dynamics: local reconsideration, retraction, or re-derivation inside long-form reasoning traces. On 6{,}000 Qwen3-8B AIME traces, we annotate segment-level backtrack severity and analyze event timing, normalized depth, and local burst structure. We find that early isolated repair is often compatible with correct reasoning, whereas incorrect traces more often show moderate-to-severe backtracks that persist and cluster late. Cross-corpus checks show the same qualitative asymmetry across additional model/domain pairs. Filtering analyses instantiate the signal as a prefix-causal selective early-exit policy: at shallow and intermediate depths, burst-aware filtering outperforms fixed length-based filtering while using only prefix-available features. Moderate length cutoffs remain strong completed-trace baselines, but burst-aware control provides a deployable mechanism for separating recoverable repair from likely instability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。