One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915904125665280 |
|---|---|
| author | Lu, Yuxing Lin, Yushuhong Zhang, Jason |
| author_facet | Lu, Yuxing Lin, Yushuhong Zhang, Jason |
| contents | Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from one role-conditioned distribution, and multi-agent frameworks use fixed roles with flat majority voting, discarding the diagnostic signal in disagreement. We propose CAMP (Case-Adaptive Multi-agent Panel), where an attending-physician agent dynamically assembles a specialist panel tailored to each case's diagnostic uncertainty. Each specialist evaluates candidates via three-valued voting (KEEP/REFUSE/NEUTRAL), enabling principled abstention outside one's expertise. A hybrid router directs each diagnosis through strong consensus, fallback to the attending physician's judgment, or evidence-based arbitration that weighs argument quality over vote counts. On diagnostic prediction and brief hospital course generation from MIMIC-IV across four LLM backbones, CAMP consistently outperforms strong baselines while consuming fewer tokens than most competing multi-agent methods, with voting records and arbitration traces offering transparent decision audits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00085 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction Lu, Yuxing Lin, Yushuhong Zhang, Jason Artificial Intelligence Computation and Language Multiagent Systems Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent predictions under minor prompt changes. Existing single-agent strategies sample from one role-conditioned distribution, and multi-agent frameworks use fixed roles with flat majority voting, discarding the diagnostic signal in disagreement. We propose CAMP (Case-Adaptive Multi-agent Panel), where an attending-physician agent dynamically assembles a specialist panel tailored to each case's diagnostic uncertainty. Each specialist evaluates candidates via three-valued voting (KEEP/REFUSE/NEUTRAL), enabling principled abstention outside one's expertise. A hybrid router directs each diagnosis through strong consensus, fallback to the attending physician's judgment, or evidence-based arbitration that weighs argument quality over vote counts. On diagnostic prediction and brief hospital course generation from MIMIC-IV across four LLM backbones, CAMP consistently outperforms strong baselines while consuming fewer tokens than most competing multi-agent methods, with voting records and arbitration traces offering transparent decision audits. |
| title | One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction |
| topic | Artificial Intelligence Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2604.00085 |