arXiv cs.CL· Yanru Xiao, Yingwei Yu·· 11 小时前AI 评分31
带搜索能力的 LLM 智能体中的认知偏差特征：一项分阶段解析分析
Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis
AI 导读
研究用受控搜索环境考察结果顺序、既往失败记录与初始假设如何影响带搜索能力的 LLM 智能体，覆盖 10 个模型和 1,000 个合成搜索世界。结果显示，主动搜索时最终答案对初始证据顺序更敏感；死胡同历史相比中性历史会减少策略切换，且该效应超出上下文长度的影响。在错误假设下，分阶段测量可区分检索或打开减少与打开反证后仍持续的错误。
正文 · 原文
Abstract:Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use. Drawing on cognitive-bias paradigms, we develop a controlled search harness to examine result order, records of prior work, and initial hypotheses while holding each question and document collection fixed. Matched controls distinguish order effects from differences in document composition and the effects of failed work from context length. Across 10 models and 1,000 synthetic search worlds, we track queries, retrieved documents, document openings, and final answers. Our comparisons suggest that final answers are more sensitive to initial evidence order during active search than when all evidence is supplied in full. Dead-end histories can reduce strategy switching relative to matched neutral histories, indicating an effect beyond context length. Under wrong hypotheses, stage measurements distinguish reduced retrieval or opening from errors that persist after counter-evidence is opened. Exploratory interventions show that opening counter-evidence more often can coincide with lower accuracy, while accuracy can improve with little change in opening.
| Comments: | 19 pages, 4 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.05720 [cs.CL] |
| (or arXiv:2611.05720v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05720 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yanru Xiao [view email]
[v1]
Tue, 3 Nov 2026 22:46:55 UTC (163 KB)
来源：arXiv cs.CL · arxiv.org