让AI在推理时动态生成工具，解决科学计算中工具匮乏难题
Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
- 推理时自主合成、验证并迭代可执行工具
- 在1590个任务上达最优准确率与工具使用效率
- 适合需要动态构建计算方法的科研型AI系统
AI在科学领域的核心挑战并非单纯推理，而是能在开放科学环境中构建计算方法的能力。现有基于大模型的智能体依赖静态预定义工具库，这一范式在科学领域因工具稀少、异构且天然不完整而失效。本文提出测试时工具演化（TTE）新范式，使智能体在推理过程中能合成、验证并演化可执行工具。通过将工具从固定资源转变为问题驱动的产物，TTE克服了静态工具库的僵化与长尾缺陷。为支持严谨评估，我们构建了包含1,590个科学推理任务和925个自动生成工具的SciEvo基准。大量实验表明，TTE在准确率与工具效率上均达到当前最佳水平，并实现跨域计算工具的有效迁移。代码与基准已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。