按年被提到
20252025 · 1 次2026
强化学习与智能体›大模型智能体·arXiv:2502.08235 · cs.AI

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Alejandro Cuadron, Dacheng Li, Wenjie Ma, Xingyao Wang, Yichuan Wang, Siyuan Zhuang, Shu Liu, Luis Gaspar Schroeder, Tian Xia, Huanzhi Mao, Nicholas Thumiger, Aditya Desai 等 16 人 · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-02-15 · 最近 2026-05-08
2不同的人
2活跃月份
2讨论串
43被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论languid-photic · 2026-05

“It’s mostly a bandwidth thing. We’ve seen the pattern consistently, but haven’t had time yet to write up the analysis carefully. We are not the only ones to see the reasoning inversion.: https://arxiv.org/abs/2510.11977, https://arxiv.org/abs/2502.08235, https://arxiv.org/abs/2507.14417”

GPT-5.5 Price Increase: What It Costs原评论 ↗
被提交为 story · 1 次