Uncertainty-Aware Clarification in LLM Agents with Information Gain

2026-06-02

AI Summary

This work addresses the challenge of tool misuse by large language model (LLM) agents when user instructions are ambiguous, often stemming from uncertain intent. To mitigate this, the authors propose a goal-oriented clarification framework that encourages agents to actively ask questions to reduce intent uncertainty. The approach integrates Bayesian belief updating with an information-gain reward mechanism, combining Bayesian inference, reinforcement learning, and LLM fine-tuning to enable clarification-augmented agent interactions within the τ-Bench environment. Experimental results demonstrate that this method improves average task success rates by 3.7% across five heterogeneous agents while incurring only a marginal increase of 0.3 interaction steps, substantially enhancing task completion performance under ambiguous instructions.

Abstract

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.

Problem

• uncertainty
• clarification
• user intent
• LLM agents
• ambiguous instructions

Innovation

• Information Gain Reward
• Uncertainty-Aware Clarification
• Goal-Oriented Clarification
• Bayesian Belief Update
• LLM Agents