Goal-Persistent Coding Agents as Scientific Performance Engineers: A Fixed-Radius Nearest-Neighbor Case Study

arXiv cs.AISeptember 29, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.31980v1 Announce Type: new Abstract: Coding agents can pursue persistent objectives across many tool-use turns, but evidence that general-purpose agents can conduct rigorous scientific performance engineering remains limited. We present a repository-scale case study in which off-the-shelf Codex and Claude Code agents optimize fixed-radius nearest-neighbor (FRNN) search for particle tracking. Starting from a PyTorch-dependent CUDA implementation, the agents follow an executable goal that specifies exact-correctness tests, profiling requirements, and acceptance criteria without prescribing code transformations. In the primary sequential trajectory, they autonomously remove the PyTor

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Anthropic
• Verktyg
• Forskning
• Agenter