Featured ICLR 2026 Poster First author
BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
Deepro Choudhury, Sinead Williamson, Adam Goliński, Ning Miao, Freddie Bickford Smith, Michael Kirchhof, Yizhe Zhang, Tom Rainforth
BED-LLM picks each question by maximising its expected information gain, estimated from the LLM’s own predictive distribution, and substantially improves how well LLMs gather information over many turns.
+37.4 points mean success over direct prompting (20 Questions) arXiv:2508.21184v3, Section 1
Abstract
We propose a general-purpose approach for improving the ability of large language models (LLMs) to intelligently and adaptively gather information from a user or other external source using the framework of sequential Bayesian experimental design (BED). This enables LLMs to act as effective multi-turn conversational agents and interactively interface with external environments. Our approach, which we call BED-LLM (Bayesian experimental design with large language models), is based on iteratively choosing questions or queries that maximize the expected information gain (EIG) with respect to a variable of interest given the responses gathered previously. We show how this EIG can be formulated (and then estimated) in a principled way using a probabilistic model derived from the LLM’s predictive distributions and provide detailed insights into key decisions in its construction and updating procedure. We find that BED-LLM achieves substantial gains in performance across a wide range of tests based on the 20 Questions game and using the LLM to actively infer user preferences, compared to purely prompting-based design generation and other adaptive design strategies.
BibTeX
Cite as Choudhury et al., “BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design”, ICLR 2026.
@inproceedings{choudhury2026bedllm,
title={{BED}-{LLM}: Intelligent Information Gathering with {LLM}s and Bayesian Experimental Design},
author={Choudhury, Deepro and Williamson, Sinead and Goli{\'n}ski, Adam and Miao, Ning and Bickford Smith, Freddie and Kirchhof, Michael and Zhang, Yizhe and Rainforth, Tom},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=qyylZMLYT8}
}