Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery

arXiv:2610.03872v1 Announce Type: cross Abstract: AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers, execution feedback can expose poor performance, but rarely reveals its underlying cause and how to address it. We introduce Auto-Diagnosis and Skill Discovery (ADSD), a framework that links numerical diagnosis to reusable solver self-improvement. ADSD follows a diagnosis-first paradigm that first explains why a solver performs poorly, then uses this diagnosis to guide the discovery of appropriate numerical methods. The resulting knowledge is packaged into reusable solver skills, turning solver improvement from trial-and-error editing into a structured process of diagnosis, discovery, and implementation. Across four challenging numerical domains--power flow equation, AC optimal power flow control, stiff ordinary differential equations, and heterogeneous diffusion PDEs--ADSD consistently improves solver accuracy, robustness, and efficiency. On GOC-500 power flow, for example, ADSD reduces mean solver error by nearly 71imes, with improvements further transferring to unseen grid topologies and operating regimes.

Related

• Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery
• Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models
• RLPF: Reinforcement Learning from Performance Feedback for Code Generation

Source: arXiv cs.LG | 2026-10-06