Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents
On the map: LLM agents and tool use → Medical and scientific domain agents
also in 1 more
Abstract (arXiv)
Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence. We study this setting by framing oncology clinical development as an offline decision-making problem in which an agent predicts the next six-month trial portfolio of an oncology drug program from information available at the decision date. To support this, we construct a temporal dataset that combines 31.7k heterogeneous public data records, including trial registries, regulatory reviews, sponsor filings, utilization data, and epidemiology, into 881 offline decision episodes across 45 historical programs. We compare four offline objectives: behavioral cloning, reward-weighted behavioral cloning, learned-reward training, and value-based implicit Q-learning against four frontier LLM agents that share a common date-gated retrieval scaffold across held-out drug, sponsor, drug-class, and temporal splits. Models trained offline outperform the non-fine-tuned baselines, particularly in the post-August 2025 contamination-clean holdout. Reward-weighted behavioral cloning performs the best, obtaining 46.2% indication F1 and 14.2% strict F1 against 25.0% and 2.1%, respectively, for the best-performing tool agent on each metric. These results suggest that structured offline learning can teach agents to plan clinical experiments.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 16 references that are in the map. First posted on arXiv 4 Aug 2026.
Builds on
13 of 16 references.
Closest ancestors · 1
Same direction, newest first
- 2024AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments13 May
Other references · 12
- 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
- 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
- 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
- 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 782
- 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
- 2020Critic Regularized Regressioncited by 275
- 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 231
- 2022When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?cited by 89
- 2022When does return-conditioned supervised learning work for offline reinforcement learning?cited by 76
- 2023Matching Patients to Clinical Trials with Large Language Modelscited by 69
- 2021HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Datacited by 49
- 2024TrialBench: Multi-Modal Artificial Intelligence-Ready Clinical Trial Datasetscited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions
- 2025Reinforcement Learning enhanced Online Adaptive Clinical Decision Support via Digital Twin powered Policy and Treatment Effect optimized Reward
- 2026Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry
- 2026Reinforcement Learning In Partially Verifiable Environments for Colon Cancer Treatment Planning
- 2023Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications
- 2025Pragmatic Policy Development via Interpretable Behavior Cloning
- 2024Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment
- 2026Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning