思考使大语言模型代理变得内向：强制性思考在用户参与代理中的反效果
Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents
AI总结：
本文研究了强制性思考在用户参与代理中的反效果，发现其导致性能下降，而主动透明性可提升代理性能。
摘要：
诱导推理已成为提高大型语言模型（LLMs）在复杂任务上的性能的一种强大技术，通过引发思考。然而，它们在现实的用户参与代理场景中的有效性仍不清楚。在本文中，我们对用户参与的LLM代理中的显式思考效果进行了全面研究。我们的实验涵盖了七种模型、三个基准测试和两种思考实例，并通过定量响应分类分析和定性失败传播案例研究来评估它们。与预期相反，我们发现强制性思考经常在用户参与的设置中产生反效果，导致各种LLM的异常性能下降。我们的关键发现揭示了思考使代理变得更加“内向”，通过缩短响应并减少向用户披露信息，从而削弱了代理与用户的信息交流，导致下游任务失败。此外，我们证明了显式提示信息披露可以可靠地提高不同模型家族的性能，表明主动透明性是代理优化的重要杠杆。总体而言，我们的研究表明，信息透明度意识是未来现实场景中推理代理设计中至关重要的但尚未被充分探索的视角。我们的代码可在https://github.com/deeplearning-wisc/Thinking-Agent上获得。
英文摘要：
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 task policies, tool results, and environment states that the user does not observe. 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: user-invisible reasoning does not necessarily translate into timely user-facing information disclosure. We introduce information disclosure as a measurable communication mechanism, covering state corrections, available options, constraints, consequences, and proactively retrieved environment information. We use this perspective to analyze the widely used user-invisible ``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 analyze response scaling under different think efforts and find that more internal thinking does not reliably translate into richer user-facing communication. Using evidence-grounded probing and turn-level counterfactual intervention, we show that injecting golden decision-relevant information produces the clearest improvement in First Edit Correction Rate, outperforming verbosity and direct think-content controls. This indicates that missing disclosure can causally affect the agent's immediate downstream environment-edit behavior. We further find that a lightweight disclosure-aware prompt mitigates degradation from enforced thinking. These results suggest that the key challenge is not simply making agents think more, but ensuring that private reasoning and environment knowledge are externalized as timely, user-facing information disclosure.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
