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
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
- EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes (NeurIPS 2024 · similarity 0.86)
- Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning (ICML 2024 · similarity 0.86)
- QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training (NeurIPS 2025 · similarity 0.86)
- MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning (ICLR 2026 · similarity 0.85)
- MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology (NeurIPS 2025 · similarity 0.85)
- Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving (ICML 2025 · similarity 0.85)
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.
