AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time Search

Yucheng Zhou, Peng Luo, Jianbing Shen

NeurIPS 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes treating medical LLMs as medical world models that jointly learn clinical policy (diagnosis and treatment proposals) and outcome dynamics, with test-time search over candidate plans.

Problem

Clinical decision-making is sequential: clinicians must propose diagnoses and treatments from pre-treatment state and anticipate post-treatment outcomes. Existing medical world models only partially address this loop (image-to-image dynamics with separate diagnostic and scoring modules, text-only tr

Approach

Unifies policy and dynamics learning within a single medical LLM so the same model proposes plans and predicts post-treatment outcomes, then uses test-time search over these predictions to revise plans.

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