作者位次 #6/7ACL 2026Poster· Natural Language Processing
Value of Information: A Framework for Human–Agent Communication
Yijiang River Dong · Tiancheng Hu · Zheng Hui · Caiqi Zhang · Ivan Vulić · Andreea Bobu · Nigel Collier
摘要
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...