Metraipolis › archive › dc_aa07488a04e1

AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments — arXiv:2610.31326

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31326
License (as archived)
CC0-1.0
Archived
2026-10-25T08:35:32.101Z
SHA-256 of the archived text
db023f84d9b4db2035753b3f7217567dc8f4a3bd38ca348d2a2ce2b570c38a09
Stable URL of this page
https://metraipolis.com/documento/dc_aa07488a04e1

How to cite

AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments — arXiv:2610.31326 — arXiv (en), https://arxiv.org/abs/2610.31326 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa07488a04e1 (Metraipolis archive dc_aa07488a04e1, sha256 db023f84d9b4db2035753b3f7217567dc8f4a3bd38ca348d2a2ce2b570c38a09)
BibTeX
@misc{dcaa07488a04e1,
  title = {AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments — arXiv:2610.31326},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31326},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa07488a04e1; sha256 db023f84d9b4db2035753b3f7217567dc8f4a3bd38ca348d2a2ce2b570c38a09},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31326. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evolutionary program search with large language models keeps the structure of an evolutionary algorithm and uses the model as its variation operator. Typically, the model generates each candidate program in a single request from parent programs and their scores. We present AgenticEvolve, an evolutionary program search framework in which each island is run by a persistent large language model agent. Between evaluations, the agent designs and runs experiments on the candidate program. To measure the contribution of experimentation, we compare AgenticEvolve with No-analysis, an otherwise identical configuration with experiments disabled. On two heuristic design tasks with three large language models, AgenticEvolve produces better programs than No-analysis and OpenEvolve on both hidden and unseen instances. It reaches the baselines' final quality with far fewer evaluations and comparable cost. On twelve equation discovery problems, it recovers the ground-truth structure of more equations than No-analysis and existing language-model and genetic programming baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.31326 — 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 2026-10-25T08:31:13.253Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).