Metraipolis › archive › dc_bd7302d52b8b
Proof-Carrying Evolution: Black-Box Search, White-Box Flight — arXiv:2610.42043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.42043
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:23:46.025Z
- SHA-256 of the archived text
86650d61f65daa079cd51c96d171cd60d3a76afda6f5fd9814b372c5b5b6739d- Stable URL of this page
https://metraipolis.com/documento/dc_bd7302d52b8b
How to cite
Proof-Carrying Evolution: Black-Box Search, White-Box Flight — arXiv:2610.42043 — arXiv (en), https://arxiv.org/abs/2610.42043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd7302d52b8b (Metraipolis archive dc_bd7302d52b8b, sha256 86650d61f65daa079cd51c96d171cd60d3a76afda6f5fd9814b372c5b5b6739d)
BibTeX
@misc{dcbd7302d52b8b,
title = {Proof-Carrying Evolution: Black-Box Search, White-Box Flight — arXiv:2610.42043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.42043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd7302d52b8b; sha256 86650d61f65daa079cd51c96d171cd60d3a76afda6f5fd9814b372c5b5b6739d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study whether a language model can help design controllers whose behavior can be formally checked. In proof-carrying evolution (PCE), a search proposes controllers together with their certificates. Their mathematical forms are fixed; a proposer chooses their numerical parameters together. Certificate checks guide selection, and only a certified candidate can be returned. The deployed artifact is a control law and its certificate; the language model is used only during design. We compare four language models with classical search and synthesis on docking under a speed limit, pursuit of a maneuvering target, and attitude control on SO(3), using paired runs and shared proposal allowances. Certificates are checked in exact rational arithmetic during search on the linear problems. On SO(3), the search uses floating-point checks, followed by exact re-verification of every reported champion. The best run of each method also receives Lean 4 proofs of its stated control properties. On the linear problems, the strongest models beat the standard classical baselines on every run, but a classical optimizer that chooses certificates for the same objective closes most of that lead. Among the cited pursuit champions, the ranking does not survive a change from Euler to zero-order-hold dynamics. On SO(3), no model detectably outperforms CMA-ES when mixed with classical mutation. When models write every proposal, one tested model improves on CMA-ES and the other performs worse than its mixed variant. All search medians remain below the hand-tuned law. In a docking control with the objective and mutation operator held fixed, retaining certified candidates yields new certified designs in every run; removing this rule yields none. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Neural and Evolutionary Computing (cs.NE); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.42043 — 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 2026-11-03T08:06:53.849Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).