Research map / Multi-agent systems and games / LLM agents
Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning
Shuohao Gao, Xuanzhong Chen, Lingxiao Luo, Zilin Ding, Rong Han, Rui Jiang, Ting Chen
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 Salus, a multi-agent reinforcement learning approach that trains LLM-based agents to strategically request diagnostic tests over multiple rounds until reaching a definitive diagnosis of complex diseases.
Problem
LLMs used as clinical assistants struggle with the sequential, iterative process of complex diagnosis, in which clinicians must request multiple rounds of diagnostic tests to differentiate similar diseases. The abstract is truncated, so the specific failure modes beyond premature diagnosis are not s
Approach
Frames strategic diagnostic testing as a multi-agent reinforcement learning problem so that agents learn when and which diagnostic tests to request before committing to a diagnosis. Details beyond the abstract are not available.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-agent RL (DR and SC) after SFT (ablation) | Salus-Zero-7B · 269 high-complexity cases | Top-1 accuracy: 55.02 -> 83.64 | Improved |
| add RL to the Strategic Controller (in addition to DR) (ablation) | Salus-7B · 269 high-complexity cases | Top-1 accuracy: 61.71 -> 83.64 | Improved |
| add RL for DR only after SFT (ablation) | Salus-Zero-7B · 269 high-complexity cases | Top-1 accuracy: 55.02 -> 61.71 | Improved |
| add RL for SC (ablation) | Salus-7B · 269 high-complexity cases | Information sufficiency: 65.43 -> 72.86 | Improved |
| increase SFT data from 12.5% to 100% (ablation) | Salus-Zero-7B · 269 high-complexity cases | Top-1 accuracy: 44.61 -> 55.02 | Improved |
| use 7B backbone instead of 3B for SFT (ablation) | Salus-Zero · 269 high-complexity cases | Top-1 accuracy: 43.87 -> 55.02 | Improved |
| use DeepSeek-V3.1 as teacher instead of stronger DeepSeek-V3.2 (ablation) | Salus-Zero-7B · 269 high-complexity cases | Top-1 accuracy: 43.12 -> 55.02 | Improved |
| use DeepSeek-V3.1 teacher instead of GLM-Z1-Flash (ablation) | Salus-Zero-7B · 269 high-complexity cases | Top-1 accuracy: 31.97 -> 55.02 | Improved |
| increase SFT data from 50% to 100% (ablation) | Salus-Zero-7B · 269 high-complexity cases | Top-1 accuracy: 54.28 -> 55.02 | Improved |
| apply Salus RL framework to 3B backbone | Qwen2.5-3B-Instruct · 269 high-complexity cases | Top-1 accuracy: 19.33 -> 65.06 | Improved |
| apply Salus training to Qwen2.5-7B-Instruct | Qwen2.5-7B-Instruct · 269 high-complexity cases | Top-1 accuracy: 27.88 -> 83.64 | Improved |
| apply Salus training on routine cases | Qwen2.5-7B-Instruct · 483 routine cases | Top-1 accuracy: 59.63 -> 91.10 | Improved |
Limitations
- Full text unavailable; only the truncated abstract was available
Closest papers by meaning
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments (NeurIPS 2026 · similarity 0.86)
- MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis (AAAI 2026 · similarity 0.85)
- MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow (ICLR 2026 · similarity 0.85)
- Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models (NeurIPS 2025 · similarity 0.84)
- Timely Clinical Diagnosis through Active Test Selection (NeurIPS 2025 · similarity 0.84)
- MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning (ICLR 2026 · similarity 0.84)
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.
