模型过度思考会降低任务表现，优化可提升30%效率
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
- 发现模型倾向冗长推理而非环境交互，导致三类失效模式
- 过思得分越高，性能越差，推理模型更易陷入此问题
- 通过筛选低过思方案，性能提升近30%，计算成本降43%
大型推理模型在交互环境中解决问题的能力受限于一种称为‘过度思考’的现象，即模型偏好冗长的内部推理链而非与环境互动。通过对软件工程任务在SWE Bench Verified上的实验，我们观察到三种典型模式：分析瘫痪、错误动作和过早退出。构建评估框架分析4018条轨迹，发现高过思得分与低性能显著相关，推理模型比非推理模型更易过思。简单地选择过思得分较低的解法，可使模型性能提升近30%，同时降低43%的计算开销。研究建议利用原生函数调用与选择性强化学习来缓解该问题。代码与数据集已开源。
原文摘要 · Abstract (English)
Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where models favor extended internal reasoning chains over environmental interaction. Through experiments on software engineering tasks using SWE Bench Verified, we observe three recurring patterns: Analysis Paralysis, Rogue Actions, and Premature Disengagement. We propose a framework to study these behaviors, which correlates with human expert assessments, and analyze 4018 trajectories. We observe that higher overthinking scores correlate with decreased performance, with reasoning models exhibiting stronger tendencies toward overthinking compared to non-reasoning models. Our analysis reveals that simple efforts to mitigate overthinking in agentic environments, such as selecting the solution with the lower overthinking score, can improve model performance by almost 30% while reducing computational costs by 43%. These results suggest that mitigating overthinking has strong practical implications. We suggest that by leveraging native function-calling capabilities and selective reinforcement learning overthinking tendencies could be mitigated. We also open-source our evaluation framework and dataset to facilitate research in this direction at https://github.com/AlexCuadron/Overthinking.
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。