S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research

TL;DR

S1-NexusAgent is a self-evolving, hierarchical framework that enhances multidisciplinary scientific research by integrating diverse tools, managing complex workflows, and continuously improving through self-evaluation and skill distillation.

Contribution

The paper introduces S1-NexusAgent, a novel self-evolving agent framework with hierarchical planning, dynamic tool orchestration, and continuous learning capabilities tailored for complex scientific research.

Findings

Achieves state-of-the-art results on scientific benchmarks.

Effectively manages long-horizon planning and heterogeneous tools.

Demonstrates robust self-evolution and knowledge reuse.

Abstract

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.