S1-NexusAgent：一个多学科科学研究的自演化代理框架
S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research
AI总结：
S1-NexusAgent通过自演化机制和双环架构，实现多学科科学研究中的复杂工作流建模与高效工具协调，验证了其在长视界规划和复杂任务中的卓越性能。
摘要：
现代科学研究依赖大规模数据、复杂工作流和专用工具，现有大语言模型和基于工具的代理由于在长视界规划、鲁棒目标维护和持续学习方面的局限性而难以处理这些需求。为了解决这些问题，本文提出了S1-NexusAgent，一个为多学科科学研究设计的自演化代理框架。S1-NexusAgent采用分层的计划与代码执行范式，通过双环架构将全球科学规划与子任务级工具执行解耦，从而能够稳定建模复杂的科研工作流。系统原生支持模型上下文协议（MCP），集成了多达数千个跨学科科学工具，并通过意图感知的动态工具检索和热插拔机制实现异构科研工具的高效协调。为了解决科学场景中的长上下文和大规模数据挑战，S1-NexusAgent引入了基于对象引用的稀疏上下文管理，这使得子任务上下文隔离和中间结果压缩成为可能。在此基础上，一个评估代理自动评估完整的执行轨迹，并将高质量的研究路径提炼成可重用的科学技能，形成一个闭环的持续自演化机制，这对于可持续和长视界科学研究具有价值。在权威科学基准测试中，包括生物、化学和材料科学的长视界规划和复杂专用工具协调任务，S1-NexusAgent均实现了最先进的性能，验证了其在复杂科学任务中的有效性和泛化能力。
英文摘要：
Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maintenance, and continual learning from execution. To address these issues, in this work, we propose S1-NexusAgent, a self-evolving agent framework designed for multidisciplinary scientific research. S1-NexusAgent adopts a hierarchical Plan-and-CodeAct execution paradigm, decoupling global scientific planning from subtask-level tool execution through a dual-loop architecture, thereby enabling stable modeling of complex research workflows. The system natively supports the Model Context Protocol (MCP), integrates up to thousands of cross-disciplinary scientific tools, and achieves efficient orchestration of heterogeneous research tools via intention-aware dynamic tool retrieval and hot-plug mechanisms. To address long-context and large-scale data challenges in scientific settings, S1-NexusAgent introduces object-reference-based sparse context management, which enables sub-task context isolation and intermediate result compression. Building on this, a Critic Agent automatically evaluates complete execution trajectories and distills high-quality research paths into reusable Scientific Skills, forming a closed loop for continuous self-evolution, which is valuable for sustainable and long-horizon scientific research. Experiments on authoritative scientific benchmarks involving long-horizon planning and complex specialized tool orchestration, including biomini-eval (biology), ChemBench (chemistry), and MatSciBench (material science), demonstrate that S1-NexusAgent achieves state-of-the-art performance, validating its effectiveness and generalization capability in complex scientific tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
