ClinicalReTrial: A Self-Evolving AI Agent for Clinical Trial Protocol Optimization

ACL ARR 2026 January Submission6006 Authors

Keywords: Multi-agent systems, In-context learning, Clinical trial optimization, Self-evolving agents, Large language models, Healthcare, AI for Science

Abstract: Clinical trials constitute a critical yet exceptionally challenging and costly stage of drug development ($2.6B per drug), where protocols are encoded as complex natural language documents, motivating the use of AI systems beyond manual analysis. Existing AI methods predict trial failure accurately but offer no actionable remedies. To fill this gap, this paper proposes **ClinicalReTrial**, a multi-agent framework that formulates clinical trial optimization as an iterative redesign problem on textual protocols. Our method integrates failure diagnosis, safety-aware modifications, and candidate evaluation in a closed-loop, reward-driven optimization framework. Serving the outcome prediction model as a simulation environment, **ClinicalReTrial** enables low-cost evaluation and dense reward signals for continuous self-improvement. We further propose hierarchical memory capturing iteration-level feedback within trials and distilling transferable redesign patterns across trials. Empirically, **ClinicalReTrial** improves 83.3% of trial protocols with a mean success probability gain of 5.7% at negligible cost ($0.12 per trial). Retrospective case studies demonstrate strong alignment between the discovered redesign strategies and real-world clinical trial modifications.

Paper Type: Long

Research Area: Clinical and Biomedical Applications

Research Area Keywords: healthcare, clinical decision support, LLM agents, multi-agent systems, agent memory, planning in agents

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 6006