Uncertainty-Aware Clarification in LLM Agents with Information Gain

Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Ying Zhao, Zhijiang Guo, Wei Wang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:24083-24102, 2026.

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 $\tau$-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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-deng26l, title = {Uncertainty-Aware Clarification in {LLM} Agents with Information Gain}, author = {Deng, Mengyi and Li, Zhiwei and Li, Xin and Zhu, Tingyu and Zhao, Ying and Guo, Zhijiang and Wang, Wei}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {24083--24102}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/deng26l/deng26l.pdf}, url = {https://proceedings.mlr.press/v306/deng26l.html}, 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 $\tau$-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.} }
Endnote
%0 Conference Paper %T Uncertainty-Aware Clarification in LLM Agents with Information Gain %A Mengyi Deng %A Zhiwei Li %A Xin Li %A Tingyu Zhu %A Ying Zhao %A Zhijiang Guo %A Wei Wang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-deng26l %I PMLR %P 24083--24102 %U https://proceedings.mlr.press/v306/deng26l.html %V 306 %X 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 $\tau$-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.
APA
Deng, M., Li, Z., Li, X., Zhu, T., Zhao, Y., Guo, Z. & Wang, W.. (2026). Uncertainty-Aware Clarification in LLM Agents with Information Gain. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:24083-24102 Available from https://proceedings.mlr.press/v306/deng26l.html.

Related Material