Metraipolis › archive › dc_28ba765dfb16

ResidencyRL: Reinforcement Learning in Simulated Clinical Environments — arXiv:2608.07418

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07418
License (as archived)
CC0-1.0
Archived
2026-10-19T09:47:14.259Z
SHA-256 of the archived text
6aec2af306ad0455c329daa9386767764f1808e4a838cc2a2a55e2ee9e74005c
Stable URL of this page
https://metraipolis.com/documento/dc_28ba765dfb16

How to cite

ResidencyRL: Reinforcement Learning in Simulated Clinical Environments — arXiv:2608.07418 — arXiv (en), https://arxiv.org/abs/2608.07418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28ba765dfb16 (Metraipolis archive dc_28ba765dfb16, sha256 6aec2af306ad0455c329daa9386767764f1808e4a838cc2a2a55e2ee9e74005c)
BibTeX
@misc{dc28ba765dfb16,
  title = {ResidencyRL: Reinforcement Learning in Simulated Clinical Environments — arXiv:2608.07418},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07418},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28ba765dfb16; sha256 6aec2af306ad0455c329daa9386767764f1808e4a838cc2a2a55e2ee9e74005c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy. Much of clinical reasoning relies on the patient encounter, a dialogue in which a clinician elicits history, refines diagnostic hypotheses, and decides management under uncertainty. While large language models (LLMs) excel on static medical benchmarks, methods to optimize the full sequence of clinical decisions remain underdeveloped. We present ResidencyRL, a reinforcement learning (RL) method for training clinical artificial intelligence (AI) agents through simulated multi-turn clinical encounters (up to 60 dialogue turns and 8 tool calls per trajectory). ResidencyRL pairs the policy agent with LLM simulators capable of complex, adversarial behaviors, training against a structured reward aligned to diagnostic accuracy, management quality, communication, documentation, and safety. On held-out evaluations, the ResidencyRL agent improves diagnostic accuracy by 7.0% under adversarial conditions (88.0% vs. 81.0%) and reduces missed red flag rates by 31%, demonstrating rigorous mitigation of premature closure. Blinded expert clinicians validated these gains, preferring the trained agent in 87.6% of side-by-side comparisons. The procedural competencies transfer to unseen benchmarks: the agent outperforms the base model across all six clinical axes of the AMIE multi-visit benchmark, and shows consistent directional improvements on AgentClinic and CRAFT-MD. Our findings demonstrate that sequential clinical decision-making can be effectively learned through multi-turn RL in simulation, yielding robust, generalizable capabilities, paving the way towards clinical mastery. Prospective validation with real-world workflows remains necessary to establish clinical utility.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.07418 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:46:37.275Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).