AI Paper Atlas

Research map / Large language models / Agents, code and math

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design

Deepro Choudhury, Sinead Williamson, Adam Golinski, Ning Miao, Freddie Bickford Smith, Michael Kirchhof, Yizhe Zhang, Tom Rainforth

ICLR 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 25 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use full EIG with non-deterministic likelihood instead of predictive entropy (ablation)BED-LLM · 20 Questionssuccess rate (%): 79 -> 88 (GPT-4o-mini, Animals)Improved
use prior-likelihood pairing instead of data-estimation pairing (ablation)BED-LLM · 20 Questionssuccess rate (%): 70 -> 93 (GPT-4o, Animals)Improved
filter hypotheses for consistency with history instead of raw in-context beliefs (ablation)BED-LLM · 20 Questionssuccess rate (%): 25 -> 93 (GPT-4o, Animals)Improved
select questions by explicit EIG estimation instead of LLM judgment (ablation)BED-LLM · 20 Questionssuccess rate (%): 70 -> 93 (GPT-4o, Animals)Improved
add BED-LLM question selection over direct promptingLLM questioner · 20 Questionssuccess rate (%): 45 -> 93 (GPT-4o, Animals)Improved
add BED-LLM over direct prompting across setupsLLM questioner · 20 Questionssuccess rate (%): +37.4 percentage points on averageImproved
add chain-of-thought to prompt-only questioningPrompt-Only · 20 Questionssuccess rate (%): 45 -> 62 (GPT-4o, Animals); 10 -> 10 (Llama-3.1-8B, Things)Mixed
use Split (hypothesis-splitting) over Prompt-OnlyPrompt-Only · 20 Questionssuccess rate (%): 45 -> 83 (GPT-4o, Animals)Improved
use Entropy ablation in preference elicitation instead of full EIG (ablation)BED-LLM · Preference elicitationmean film ratingNo clear effect
add BED-LLM in preference elicitationLLM questioner · Preference elicitationmean film ratingImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy