arXiv：cs.AI· Pengcheng Hou, Xiaojun Tan, Sihan Hu, Ruisi Wang, Shuo Chen, Lei Wang, Youjin Deng, Kun Chen·· 23 小时前
AI 智能体递归改进可微分科学软件生态
Recursive Improvement of a Differentiable Scientific Software Ecosystem
AI 导读
一个面向 AI 编程智能体的环境被提出，用于推动可微分科学软件的持续演化，将需求识别、开发与质量评估串联起来。研究在物理、化学和生物建模领域的 20 个软件包中构建并验证了自动微分扩展，benchmark 显示梯度评估相比有限差分法更省算力，并能完成参数估计。量子控制与热设计研究据此修改目标函数，在复用现有导数的同时改进设计。
正文
Abstract:Differentiable programming connects scientific computation with gradient-based inference, learning and design. Extending these capabilities across a heterogeneous software ecosystem requires specialized effort to implement derivatives, integrate interfaces and evaluate quality. AI coding agents can accelerate this transformation, but translating their capabilities into useful scientific software requires identifying research needs and evaluating how well implementations meet them. We present an environment for agent-driven evolution of differentiable scientific software that connects demand identification, development and quality evaluation. A unified differentiation interface exposes reusable derivative rules alongside existing numerical routines, allowing research tasks to share these capabilities. Research requirements guide development, with implementations assessed through independent derivative checks, workflow tests and performance evaluation. Validated software, research programs and tests become shared resources for subsequent studies. We construct and validate automatic differentiation extensions across 20 packages spanning physical, chemical and biological modeling, with research workflows demonstrating reuse across tasks. Benchmarks demonstrate computational savings over finite differences in gradient evaluation and complete parameter estimation. Research-driven revisions make previously unsupported workflows differentiable, correct derivatives of scientific observables and eliminate redundant computation. Quantum-control and thermal-design studies revise objectives in response to physical evaluation, improving designs while reusing existing derivatives. This work provides a practical approach to expanding differentiable programming across established scientific software and organizing AI agents around the recursive improvement of a shared computational ecosystem.
| Subjects: | Artificial Intelligence (cs.AI); Computational Physics (physics.comp-ph) |
| Cite as: | arXiv:2610.04561 [cs.AI] |
| (or arXiv:2610.04561v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.04561 arXiv-issued DOI via DataCite |
Submission history
From: Pengcheng Hou [view email]
[v1]
Sat, 3 Oct 2026 14:51:09 UTC (728 KB)
[v2]
Mon, 12 Oct 2026 08:01:04 UTC (728 KB)
来源：arXiv：cs.AI · arxiv.org