CAi Copilot：通过意图驱动的智能体工作流减少分子设计中的操作工作量

中文摘要 AI 辅助

早期分子设计是一个迭代过程，而非仅生成分子的任务。研究人员需将宽泛目标转化为设计策略，优化候选分子，评估多种性质，收集证据后再进行合成与测试。AI方法可生成分子、优化多个目标、预测性质、对接化合物并考虑合成可行性，但这些功能分散在各类专用工具中，专家仍需协调各步骤、判断中间结果并整合证据。核心挑战在于将研究意图转化为基于科学工具的自适应、可追溯的运行流程。我们将此挑战视为“意图到证据”的分子设计工作流执行问题，提出了CAi Copilot——一种面向专家的智能体，包含三个关联层级：研究接口层将意图转化为可执行计划；智能体推理层利用中间结果指导每一步运行；执行底层提供分子工具、度量指标、可复用工具及后端服务。在45项任务中，CAi取得了最强的整体性能，结果得分为84.59，比次优结果高出18.07分。额外基准测试验证了CAi协调生成、筛选及多标准评估的能力，同时也揭示了其在长周期执行中的局限性。这些结果表明，CAi可将宽泛的分子设计意图转化为透明、可追溯的工作流，将中间决策与候选分子层面的证据关联起来。

英文摘要

Early-stage molecular design is an iterative process, not just a task of generating molecules. Researchers turn broad goals into design strategies, refine candidates, assess many properties, and gather evidence before synthesis and tests. AI methods can generate molecules, optimize several goals, predict properties, dock compounds, and account for synthesis. Yet these functions are spread across specialized tools. Experts must still coordinate each step, judge interim results, and integrate evidence. The central challenge is thus to turn research intent into adaptive, traceable runs grounded in scientific tools. We cast this challenge as intent-to-evidence molecular design workflow execution and present CAi Copilot, an expert-oriented agent with three linked layers. The Research Interface Layer turns intent into an executable plan. The Agent Reasoning Layer uses interim results to guide each run. The Execution Substrate supplies molecular tools, metrics, reusable utilities, and backend services. Across 45 tasks, CAi achieves the strongest overall performance, with an outcome score of 84.59, exceeding the next-best result by 18.07 points. Additional benchmarks test how CAi coordinates generation, screening, and multi-criteria evaluation, while exposing limits in long-horizon execution. These results show that CAi turns broad molecular-design intent into transparent, traceable workflows that connect interim decisions to candidate-level evidence.

发表机构

• Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
• Nanjing University（南京大学）

机构由 AI 辅助整理，请以论文原文为准。