Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Value of Information: A Framework for Human-Agent Communication

About

Large Language Model (LLM) agents deployed for real-world tasks face a fundamental dilemma: user requests are underspecified, yet agents must decide whether to act on incomplete information or interrupt users for clarification. Existing approaches either rely on brittle confidence thresholds that require task-specific tuning, or fail to account for the varying stakes of different decisions. We introduce a decision-theoretic framework that resolves this trade-off through the Value of Information (VoI), enabling agents to dynamically weigh the expected utility gain from asking questions against the cognitive cost imposed on users. Our inference-time method requires no hyperparameter tuning and adapts seamlessly across contexts-from casual games to medical diagnosis. Experiments across four diverse domains (20 Questions, medical diagnosis, flight booking, and e-commerce) show that VoI consistently matches or exceeds the best manually-tuned baselines, achieving up to 1.36 utility points higher in high-cost settings. This work provides a parameter-free framework for adaptive agent communication that explicitly balances task risk, query ambiguity, and user effort.

Yijiang River Dong, Tiancheng Hu, Zheng Hui, Caiqi Zhang, Ivan Vuli\'c, Andreea Bobu, Nigel Collier• 2026

Related benchmarks

TaskDatasetResultRank
Flight RecommendationFlight Rec.
Reward0.36
22
Mixed 20 QuestionMixed 20Q
Acc (Animal)76
22
Online ShoppingWebshop
LLM Score0.63
22
Question Asking Policy EvaluationMixed 20 Question
RVOI8.64
5
Showing 4 of 4 rows

Other info

Follow for update