PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

Excerpt

arXiv:2608.14441v1 Announce Type: new Abstract: Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery after those conditions change. To address this gap, we introduce PACE-Bench (Physics Adaptation via Code Evolution), a simulator-grounded benchmark of 144 source-to-target adaptation pairs across six physics domains. Each pair links a source environment to a mutated target en