Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
This addresses the challenge of open-ended scientific reasoning for AI systems, representing a new paradigm rather than an incremental improvement.
The paper tackles the problem of AI for science by addressing the limitations of static tool libraries in LLM-based agents, proposing Test-Time Tool Evolution (TTE) to synthesize and evolve tools during inference, achieving state-of-the-art performance in accuracy and tool efficiency on the SciEvo benchmark with 1,590 tasks.
The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that fundamentally fails in scientific domains where tools are sparse, heterogeneous, and intrinsically incomplete. In this paper, we propose Test-Time Tool Evolution (TTE), a new paradigm that enables agents to synthesize, verify, and evolve executable tools during inference. By transforming tools from fixed resources into problem-driven artifacts, TTE overcomes the rigidity and long-tail limitations of static tool libraries. To facilitate rigorous evaluation, we introduce SciEvo, a benchmark comprising 1,590 scientific reasoning tasks supported by 925 automatically evolved tools. Extensive experiments show that TTE achieves state-of-the-art performance in both accuracy and tool efficiency, while enabling effective cross-domain adaptation of computational tools. The code and benchmark have been released at https://github.com/lujiaxuan0520/Test-Time-Tool-Evol.