Metraipolis › archive › dc_0cb33a2ea34e

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments — arXiv:2608.14441

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14441
License (as archived): CC0-1.0
Archived: 2026-10-19T02:20:50.249Z
SHA-256 of the archived text: 4ffc6b16ddeae807eefddf19b5c0bef5dc4422ecab8075d62921b5459ef7363b
Stable URL of this page: https://metraipolis.com/documento/dc_0cb33a2ea34e

How to cite

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments — arXiv:2608.14441 — arXiv (en), https://arxiv.org/abs/2608.14441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0cb33a2ea34e (Metraipolis archive dc_0cb33a2ea34e, sha256 4ffc6b16ddeae807eefddf19b5c0bef5dc4422ecab8075d62921b5459ef7363b)

BibTeX

@misc{dc0cb33a2ea34e,
  title = {PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments — arXiv:2608.14441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0cb33a2ea34e; sha256 4ffc6b16ddeae807eefddf19b5c0bef5dc4422ecab8075d62921b5459ef7363b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 environment with the same goal and interface. A code-driven design that succeeds in the source fails in the target, where agents must iteratively adapt it into a working target design using diagnostic sandbox feedback within a limited attempt budget. We compare ten self-evolving methods from four paradigms. The benchmark remains far from saturated: Reflexion + Qwen3-14B succeeds on only 35.9\% of full-benchmark pairs, while GPT-5.5 solves 66.7\% of the Statics subset under the full budget. Together, these results show that simulator-grounded reflection is more reliable than unverified self-revision, while memory anchors agents to early designs and broad tree search explores without converging. Even revealing exact physical changes does not raise the performance ceiling, pointing to mechanism redesign rather than parameter inference as the central bottleneck. Data and code are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14441 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:02:02.822Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).