让大模型主动提问来消除意图模糊，提升任务成功率。
Uncertainty-Aware Clarification in LLM Agents with Information Gain
- 用信息增益衡量提问价值，引导模型问关键问题。
- 实验显示成功率提升3.7%，平均多0.3步交互。
- 适合需要精准理解用户意图的智能助手场景。
大型语言模型（LLM）代理常面临用户指令不明确的问题，隐含的意图不确定性会导致错误的工具操作。为此，我们提出一种目标导向的澄清框架，将澄清行为与歧义消解对齐。核心是信息增益奖励，该度量通过贝叶斯信念更新量化澄清问题的效用。我们使用此奖励训练澄清模块（LLM），以优化高信息增益，确保澄清能有效降低不确定性，并在代理-工具-用户环境中提升任务完成率。我们在增强版τ-Bench环境中验证了该框架，对五种异构骨干模型进行跨代理评估。结果表明，相比无澄清基线，本方法成功率平均提升3.7%，仅增加0.3次平均交互步骤。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this challenge, we propose a goal-oriented clarification framework that aligns clarification behavior with ambiguity resolution. Central to our approach is the Information Gain Reward, a metric that quantifies the utility of clarification questions by measuring the Bayesian belief update towards the ground-truth goal induced by the clarification exchange. We train the clarifier (LLM) using this reward to optimize for high information gain, ensuring that clarifications effectively reduce uncertainty and improve task completion within the agent-tool-user environment. We validate our framework within a clarification-enhanced $τ$-Bench environment, conducting cross-agent evaluations across five heterogeneous backbones. Empirical results demonstrate that our method consistently improves the success rate by 3.7\% over the no-clarification baseline, while adding only 0.3 total interaction steps on average.
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。