跳到正文
arXiv cs.CL· Jiatong Li, Changdae Oh, Hyeong Kyu Choi, Jindong Wang, Sharon Li·· 9 小时前AI 评分38

研究揭示用户服务型 LLM 智能体的信息披露出错模式:思考不等于告知

Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents

AI 导读

研究将“信息披霞”定义为可测量的沟通机制,涵盖状态纠正、可选方案、约束条件、后果说明与主动检索的环境信息。在五个模型、三个用户服务场景中,强制思考的效用并不稳定,思考更多也不能可靠转化为更充分的信息披露;回合级反事实干预显示,注入关键决策信息能显著纠正智能体的行动轨迹,失败轨迹最常缺失状态纠正与约束说明,轻量级的披露感知提示词可有效缓解性能退化。

正文 · 原文

View PDF HTML (experimental)

Abstract:User-engaged LLM agents increasingly operate in service scenarios where task success depends on coordination between the agent, the user, and a stateful environment. In such interactions, the agent often has access to rich information that the user does not observe, such as task policies, tool results, and environment states. This makes agent-user communication a central component of task completion. In this work, we study a communication-level failure mode of user-service agents: internal reasoning is counterproductive for the interactive information disclosure. We introduce information disclosure as a measurable communication mechanism, covering state corrections, available options, constraints, consequences, and proactively retrieved environment information. Motivated by recent advances in LLM reasoning, we evaluate and analyse information disclosure under a controlled setting of agents equipped with a "think" tool, which allows agents to reason internally before responding or acting. Across five models and three user-service scenarios, we first show that enforced thinking has unstable utility. We then analyse response scaling under different think efforts and find that more thinking does not reliably translate into richer information disclosure. Using turn-level counterfactual intervention, we show that injecting golden decision-relevant information significantly intervenes agents to correct action trajectories, indicating that missing disclosure can causally affect the agent's immediate downstream behaviour. We further find that failed trajectories most often lack state corrections and constraints, and that a lightweight disclosure-aware prompt effectively mitigates degradation. These results suggest that the key challenge is not simply making agents think more, but ensuring that reasoning and information are externalised as timely information disclosure.
Comments: TMLR
Subjects: Computation and Language (cs.CL)
Cite as: arXiv:2602.07796 [cs.CL]
  (or arXiv:2602.07796v3 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2602.07796

arXiv-issued DOI via DataCite

Submission history

From: Jiatong Li [view email]
[v1] Sun, 8 Feb 2026 03:23:22 UTC (280 KB)
[v2] Sat, 8 Aug 2026 04:34:47 UTC (891 KB)
[v3] Tue, 17 Nov 2026 16:09:19 UTC (906 KB)

来源:arXiv cs.CL · arxiv.org