发表机构
Hunan University; Nanjing University; The Chinese University of Hong Kong; Zhejiang University; Yale University; Wuhan University of Science and Technology; Southeast University; Stanford University（湖南大学; 南京大学; 香港中文大学; 浙江大学; 耶鲁大学; 武汉科技大学; 东南大学; 斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AgentFold是将蛋白质折叠模型开发转化为闭环搜索的多智能体框架，以ESMFold为起点，通过MCTS策略分配计算资源，在匹配预算下较Codex提案提升lDDT 7.5%，优于随机搜索。
AI 中文摘要
科学大语言模型智能体在文献推理、工具使用和实验规划中已展现出潜力，但目前尚不清楚它们能否通过可执行代码修改和高计算成本验证自主改进大型、紧密耦合的科学机器学习系统。我们在蛋白质折叠领域研究该问题，该领域的进展需要协调的架构修改、多目标评估和领域感知解释。我们提出AgentFold，这是一个多智能体框架，将折叠模型开发表述为对可执行代码变体的闭环搜索。从ESMFold出发，AgentFold提出假设、实现并调试代码级修改、评估模型变体、分析实验结果，并将成功和失败的干预都存储在结构化记忆中。一种MCTS风格的策略在高评分搜索分支间分配计算资源。在一个包含2000多行代码的工程规模蛋白质折叠代码库上，AgentFold探索了约80个模型变体，使用了约5000 GPU小时和1.7亿个LLM token。在匹配的计算预算下，AgentFold比独立的Codex提案将最佳lDDT提升了7.5%，且优于随机搜索对照。除了模型改进，所得的干预轨迹还揭示了反复出现的经验设计模式：稳定的增益往往来自早期、柔和、可学习的先验和门控细化，而直接的几何扰动和几何条件反馈常常会破坏训练的稳定性。代码和实验资源可在该https URL公开获取。
英文摘要
Scientific LLM agents have shown promise in literature reasoning, tool use, and experiment planning, but it remains unclear whether they can autonomously improve large, tightly coupled scientific machine-learning systems through executable code changes and computationally expensive validation. We study this question in protein folding, where progress requires coordinated architectural modifications, multi-objective evaluation, and domain-aware interpretation. We present AgentFold, a multi-agent framework that formulates folding-model development as a closed-loop search over executable code variants. Starting from ESMFold, AgentFold proposes hypotheses, implements and debugs code-level modifications, evaluates model variants, analyzes experimental outcomes, and stores both successful and failed interventions in structured memory. An MCTS-style policy allocates computational resources across high-scoring search branches. On an engineering-scale protein-folding codebase comprising more than 2,000 lines of code, AgentFold explores approximately 80 model variants using approximately 5,000 GPU-hours and 170 million LLM tokens. Under a matched computational budget, AgentFold improves the best lDDT by 7.5% over independent Codex proposals and outperforms a random-search control. Beyond model improvement, the resulting intervention traces reveal recurring empirical design patterns: stable gains tend to arise from early, soft, learnable priors and gated refinement, whereas direct geometric perturbations and geometry-conditioned feedback often destabilize training. The code and experimental resources are publicly available at https://github.com/lmqfly/AgentFold.
