Metraipolis › archive › dc_6adcb1bf3cd5

AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery — arXiv:2609.15820

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15820
License (as archived)
CC0-1.0
Archived
2026-10-15T22:48:08.493Z
SHA-256 of the archived text
741e7e8adc216b723263c77a93ea12708e944dd2de3e5986c87d02167121ec7a
Stable URL of this page
https://metraipolis.com/documento/dc_6adcb1bf3cd5

How to cite

AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery — arXiv:2609.15820 — arXiv (en), https://arxiv.org/abs/2609.15820 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6adcb1bf3cd5 (Metraipolis archive dc_6adcb1bf3cd5, sha256 741e7e8adc216b723263c77a93ea12708e944dd2de3e5986c87d02167121ec7a)
BibTeX
@misc{dc6adcb1bf3cd5,
  title = {AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery — arXiv:2609.15820},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15820},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6adcb1bf3cd5; sha256 741e7e8adc216b723263c77a93ea12708e944dd2de3e5986c87d02167121ec7a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15820. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined control flows. This limitation restricts adaptive reasoning, blocks cross-paradigm transfer, and overlooks richer execution feedback. To bridge this gap, we introduce an end-to-end framework, AlgoEvo, a unified agentic architecture that transforms automated algorithm discovery into an interactive, knowledge-accumulating process. An autonomous agent dynamically inspects, diagnoses, and edits code based on runtime feedback. A design skill hub decouples paradigm-specific knowledge from the core discovery engine, allowing a unified workflow to seamlessly handle single-heuristic, multi-objective, and multi-component design. Meanwhile, a hierarchical experience bank organizes search trajectories into a task-level tree to guide exploration and consolidates cross-task patterns into reusable skills. Across six representative benchmark tasks, AlgoEvo reaches state-of-the-art performance with as little as 7% of the evaluation budget and reduced token consumption, demonstrating strong intra-task accumulation, cross-task transfer, and the ability to reproduce or exceed the strongest existing methods through flexible skill activation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.15820 — 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 2026-10-15T22:29:03.371Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).