AI Paper Atlas

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

Learning When to Collaborate: Selective Multi-Agent Medical Reasoning via Uncertainty-Aware Routing

Jiacheng Hou, Xueliang Cui, Dan Lu, Ruxin Wang

NeurIPS 2026 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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

Proposes SMART-Med, a fully local multi-agent framework for multimodal medical reasoning that selectively invokes collaboration via uncertainty-aware routing instead of always-active dense agent interaction.

Problem

Existing multi-agent medical reasoning systems assume always-active dense collaboration and rely on large cloud-based models, raising privacy and efficiency concerns for practical deployment.

Approach

Replaces always-on multi-agent collaboration with an uncertainty-aware router that decides when collaboration is needed, and runs entirely with local models rather than cloud-based large models.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dense multi-agent collaboration to a single agent (ablation)Qwen3-VL-4B-Instruct · PMC-VQA (multiple-choice)accuracy: 35.3 -> 50.1Improved
replace dense collaboration with uncertainty-driven routing (no training) (ablation)Qwen3-VL-4B-Instruct MAS · PathVQA (multiple-choice)accuracy: 66.7 -> 68.6Improved
replace dense collaboration with uncertainty-driven routing (no training) (ablation)Qwen3-VL-4B-Instruct MAS · Slake (free-form)accuracy: 75.7 -> 78.2Improved
replace dense collaboration with uncertainty-driven routing (no training) (ablation)Qwen3-VL-4B-Instruct MAS · PMC-VQA (multiple-choice)accuracy: 50.1 -> 48.5Hurt
add certainty-aware accuracy reward in GRPO (ablation)SMART-Med with uncertainty routing · PMC-VQA (multiple-choice)accuracy: 48.5 -> 69.5Improved
add certainty-aware accuracy reward in GRPO (ablation)SMART-Med with uncertainty routing · PathVQA (multiple-choice)accuracy: 68.6 -> 75.0Improved
add reasoning-quality reward model in GRPO (ablation)SMART-Med with certainty-aware reward · PMC-VQA (multiple-choice)accuracy: 69.5 -> 72.5Improved
add reasoning-quality reward model in GRPO (ablation)SMART-Med with certainty-aware reward · Slake (free-form)accuracy: 82.2 -> 84.3Improved
use learned uncertainty routing instead of random routing at matched collaboration rate (ablation)SMART-Med* · Routing validation, multiple-choiceaccuracy: 65.0 -> 78.1Improved
use learned routing instead of always-collaborate with fine-tuned backbone (ablation)SMART-Med* · Routing validation, multiple-choiceaccuracy: 77.5 -> 78.1Improved
fine-tune MOA and MDAgent with the same reasoning dataset (ablation)MOA, MDAgent · PMC-VQA (multiple-choice)accuracy: MOA 51.5 -> 65.3; MDAgents 50.6 -> 67.7Improved
certainty-aware GRPO on router (ablation)SMART-Med · False-certainty rateincorrect and CERTAIN rate (%): 28.8% -> 8.6%Improved

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