arXiv AI By Xinyi Ling, Ye Liu, Reza Averly, Xia Ning

Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation

Read the original on arXiv AI →

arXiv:2604. 03924v2 Announce Type: replace-cross Abstract: Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's intent, where the algorithm must balance information acquisition and target commitment over multiple turns.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 2

CA-BED: Conversation-Aware Bayesian Experimental Design

arXiv:2606. 01182v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at static reasoning tasks, yet their performance often degrades in interactive scenarios where information must be actively acquired through questioning.

By Daniel Arnould, Rashad Aziz, Zixuan Kang, Tanav Changal, Kevin Zhu, Sunishchal Dev, Gabriel Grand, Shreyas Sunil Kulkarni
Hugging Face Trending Papers
Aug 12

Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents

Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one generated answer. For LLM agents, however, the unit of observation is an interactive trajectory, where the model can ask clarifying questions, call tools, update state, and make intermediate decisions whose errors propagate to the final outcome.