MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning

• URL: http://arxiv.org/abs/2608.30676v1
• Date: Mon, 31 Aug 2026 12:19:41 GMT
• Title: MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
• Abstract summary: We identify a systematic failure mode in RL-trained retrieval agents.<n>We address this with a faithfulness-gated reward design.<n>The resulting system, MedAgent-R1, reduces citation fabrication from 31.8% to 4.7%.
• Score: 6.676492026608371
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially reference retrieved evidence can mislead clinicians into unsafe treatment decisions. Medical reasoning agents must therefore produce not only correct answers but also faithful justifications that clinicians can verify against cited evidence. We identify a systematic failure mode in RL-trained retrieval agents: outcome-only rewards improve accuracy while degrading faithfulness, a phenomenon we term confident hallucination. The agent learns to answer from parametric memory and backfill plausible but unsupported justifications; citation fabrication rates rise from 16.5% to 31.8% even as accuracy improves by 5 points over the supervised baseline. We address this with a faithfulness-gated reward design: accuracy credit is conditioned on evidence grounding via a hard gate, complemented by retrieval validity and conciseness signals that close exploitation paths unique to agentic retrieval. The resulting system, MedAgent-R1, reduces citation fabrication from 31.8% to 4.7% and raises evidence completeness from 58.7 to 82.6 while maintaining 75.1% accuracy, with 13.2-point gains on HealthBench Safety. Under the same agentic retrieval setup, MedAgent-R1 outscores GPT-4o on faithfulness-specific dimensions (Factual Support 4.55 vs. 4.25; Overclaiming 4.40 vs. 4.15) while remaining below GPT-4o in overall accuracy, suggesting that explicit faithfulness training yields evidence-grounding gains not achieved by scaling alone.

Related papers

• MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction [8.036967404810378]
  We introduce MediSkill-Evo, which self-evolves governed process knowledge without fine-tuning the backbone.<n>On Qwen FullChain, MediSkill-Evo improves diagnosis accuracy by 7.81% and treatment-intent coverage by 70.67% over the best-performing prior agent.<n>On multimodal NEJM diagnosis, MediSkill-Evo with optional MedSAM localization improves diagnosis accuracy by 2.56% and core score by 18.96% over the best-performing memory agent.
  arXiv  Detail & Related papers  (2026-08-24T15:45:26Z)
• Trivial Prompt Reframing Bypasses Safety Guardrails in Googleś MedGemma-4B [0.0]
  Open-weight medical language models are increasingly used as the base of patient-facing and clinician-support applications.<n>We quantify that gap for MedGemma-4B-it under attacks that require no technical sophistication.
  arXiv  Detail & Related papers  (2026-07-09T18:31:43Z)
• An AI agent for treatment reasoning over a biomedical tool universe [35.05540785374698]
  We introduce ATHENA-R1, an AI agent for treatment reasoning across all FDA approved drugs since 1939.<n>ATHENA-R1 is trained by reinforcement learning over a universe of 212 biomedical tools.<n>It reaches 94.7% accuracy on open-ended drug reasoning and 82.9% on treatment reasoning.
  arXiv  Detail & Related papers  (2026-06-27T02:24:56Z)
• Measuring Epistemic Resilience of LLMs Under Misleading Medical Context [47.20527783144983]
  Large language models (LLMs) now reach expert-level scores on medical licensing exams.<n>We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer.<n>We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it.
  arXiv  Detail & Related papers  (2026-06-10T16:27:26Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away [97.11976870616273]
  We propose a lightweight inference-time defense that treats safety recovery as a satising constraint rather than an objective.<n>In our evaluations across six open-source MLRMs and four jailbreak benchmarks, SafeThink reduces attack success rates by 30-60%.
  arXiv  Detail & Related papers  (2026-02-11T18:09:17Z)
• MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine [69.08855631283829]
  We introduce Med Omni-45 Degrees, a benchmark designed to quantify safety-performance trade-offs under manipulative hint conditions.<n>It contains 1,804 reasoning-focused medical questions across six specialties and three task types, including 500 from MedMCQA.<n>Results show a consistent safety-performance trade-off, with no model surpassing the diagonal.
  arXiv  Detail & Related papers  (2025-08-22T08:38:16Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• Medical Hallucinations in Foundation Models and Their Impact on Healthcare [71.15392179084428]
  Hallucinations in foundation models arise from autoregressive training objectives.<n>Top-performing models exceeded 97% accuracy when augmented with chain-of-thought prompting.
  arXiv  Detail & Related papers  (2025-02-26T02:30:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.