[2601.00290] ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents

Computer Science > Artificial Intelligence arXiv:2601.00290 (cs) [Submitted on 1 Jan 2026 (v1), last revised 2 Apr 2026 (this version, v2)] Title:ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents Authors:Sixue Xing, Kerui Wu, Xuanye Xia, Meng Jiang, Jintai Chen, Tianfan Fu View a PDF of the paper titled ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents, by Sixue Xing and 5 other authors View PDF HTML (experimental) 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 accurately predict trial failure, but do not provide actionable remedies. To fill this gap, this paper proposes ClinicalReTrial, a multi-agent system that formulates clinical trial optimization as an iterative redesign problem on textural 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 a hierarchical memory that captures iteration-level feedback within trials and distills transferable redesign patterns across trials. Empirically, ClinicalReTrial improves $83.3\%$...