Value of Information: A Framework for Human-Agent Communication
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908756924694528 |
|---|---|
| author | Dong, Yijiang River Hu, Tiancheng Hui, Zheng Zhang, Caiqi Vulić, Ivan Bobu, Andreea Collier, Nigel |
| author_facet | Dong, Yijiang River Hu, Tiancheng Hui, Zheng Zhang, Caiqi Vulić, Ivan Bobu, Andreea Collier, Nigel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06407 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Value of Information: A Framework for Human-Agent Communication Dong, Yijiang River Hu, Tiancheng Hui, Zheng Zhang, Caiqi Vulić, Ivan Bobu, Andreea Collier, Nigel Computation and Language 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. |
| title | Value of Information: A Framework for Human-Agent Communication |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.06407 |