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
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:33039-33068, 2026.

Abstract

Diagnosing complex diseases is inherently a sequential and iterative medical investigation process, in which a clinician strategically requests multiple rounds of diagnostic tests to differentiate among similar diseases until reaching a definitive diagnosis. Although large language models show great potential as clinical assistants, they often struggle to navigate this complex interactive process, suffering from premature diagnostic closure. Furthermore, optimizing LLMs for such multi-round environments is frequently hindered by the challenge of reward sparsity and hacking. In this paper, we introduce $\textbf{CompDiag-Bench}$, a benchmark that formalizes diagnosis as a sequential decision-making process where a clinician must strategically request diagnostic tests from a dynamic environment in order to reach a definitive diagnosis. To address this task, we propose $\texttt{Salus}$, a multi-agent framework that decouples diagnostic reasoning into three specialized functional roles: a Differential Reasoner, a Strategic Controller, and a Workup Proposer. $\texttt{Salus}$ is optimized via multi-agent reinforcement learning employing structured rewards to calibrate strategic diagnostic behavior. Specifically, we leverage an LLM-as-a-Judge reward mechanism to provide dense, semantically-grounded feedback, designed to penalize premature closure and incentivize accurate differential diagnoses. Experimental results show that our model, $\texttt{Salus-7B}$, attains state-of-the-art Top-1 accuracy of $83.64%$ on complex cases, outperforming DeepSeek-V3.2 ($71.38%$) and achieving performance on par with GPT-5.2 ($80.30%$).

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-gao26c, title = {Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning}, author = {Gao, Shuohao and Chen, Xuanzhong and Luo, Lingxiao and Ding, Zilin and Han, Rong and Jiang, Rui and Chen, Ting}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {33039--33068}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/gao26c/gao26c.pdf}, url = {https://proceedings.mlr.press/v306/gao26c.html}, abstract = {Diagnosing complex diseases is inherently a sequential and iterative medical investigation process, in which a clinician strategically requests multiple rounds of diagnostic tests to differentiate among similar diseases until reaching a definitive diagnosis. Although large language models show great potential as clinical assistants, they often struggle to navigate this complex interactive process, suffering from premature diagnostic closure. Furthermore, optimizing LLMs for such multi-round environments is frequently hindered by the challenge of reward sparsity and hacking. In this paper, we introduce $\textbf{CompDiag-Bench}$, a benchmark that formalizes diagnosis as a sequential decision-making process where a clinician must strategically request diagnostic tests from a dynamic environment in order to reach a definitive diagnosis. To address this task, we propose $\texttt{Salus}$, a multi-agent framework that decouples diagnostic reasoning into three specialized functional roles: a Differential Reasoner, a Strategic Controller, and a Workup Proposer. $\texttt{Salus}$ is optimized via multi-agent reinforcement learning employing structured rewards to calibrate strategic diagnostic behavior. Specifically, we leverage an LLM-as-a-Judge reward mechanism to provide dense, semantically-grounded feedback, designed to penalize premature closure and incentivize accurate differential diagnoses. Experimental results show that our model, $\texttt{Salus-7B}$, attains state-of-the-art Top-1 accuracy of $83.64%$ on complex cases, outperforming DeepSeek-V3.2 ($71.38%$) and achieving performance on par with GPT-5.2 ($80.30%$).} }
Endnote
%0 Conference Paper %T Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning %A Shuohao Gao %A Xuanzhong Chen %A Lingxiao Luo %A Zilin Ding %A Rong Han %A Rui Jiang %A Ting Chen %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-gao26c %I PMLR %P 33039--33068 %U https://proceedings.mlr.press/v306/gao26c.html %V 306 %X Diagnosing complex diseases is inherently a sequential and iterative medical investigation process, in which a clinician strategically requests multiple rounds of diagnostic tests to differentiate among similar diseases until reaching a definitive diagnosis. Although large language models show great potential as clinical assistants, they often struggle to navigate this complex interactive process, suffering from premature diagnostic closure. Furthermore, optimizing LLMs for such multi-round environments is frequently hindered by the challenge of reward sparsity and hacking. In this paper, we introduce $\textbf{CompDiag-Bench}$, a benchmark that formalizes diagnosis as a sequential decision-making process where a clinician must strategically request diagnostic tests from a dynamic environment in order to reach a definitive diagnosis. To address this task, we propose $\texttt{Salus}$, a multi-agent framework that decouples diagnostic reasoning into three specialized functional roles: a Differential Reasoner, a Strategic Controller, and a Workup Proposer. $\texttt{Salus}$ is optimized via multi-agent reinforcement learning employing structured rewards to calibrate strategic diagnostic behavior. Specifically, we leverage an LLM-as-a-Judge reward mechanism to provide dense, semantically-grounded feedback, designed to penalize premature closure and incentivize accurate differential diagnoses. Experimental results show that our model, $\texttt{Salus-7B}$, attains state-of-the-art Top-1 accuracy of $83.64%$ on complex cases, outperforming DeepSeek-V3.2 ($71.38%$) and achieving performance on par with GPT-5.2 ($80.30%$).
APA
Gao, S., Chen, X., Luo, L., Ding, Z., Han, R., Jiang, R. & Chen, T.. (2026). Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:33039-33068 Available from https://proceedings.mlr.press/v306/gao26c.html.

Related Material