Metraipolis › archive › dc_a1ce9633005e

EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution — arXiv:2610.12086

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12086
License (as archived)
CC0-1.0
Archived
2026-10-09T05:48:30.392Z
SHA-256 of the archived text
4a7b16ebd827c096f50e95f69740748d09a9692398cd07db26cb294e81937023
Stable URL of this page
https://metraipolis.com/documento/dc_a1ce9633005e

How to cite

EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution — arXiv:2610.12086 — arXiv (en), https://arxiv.org/abs/2610.12086 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a1ce9633005e (Metraipolis archive dc_a1ce9633005e, sha256 4a7b16ebd827c096f50e95f69740748d09a9692398cd07db26cb294e81937023)
BibTeX
@misc{dca1ce9633005e,
  title = {EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution — arXiv:2610.12086},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12086},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a1ce9633005e; sha256 4a7b16ebd827c096f50e95f69740748d09a9692398cd07db26cb294e81937023},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12086. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based program evolution relies on evaluation feedback to guide the iterative search for high-performing programs. However, evaluation is often computationally expensive, making it essential to allocate limited resources to candidates that can most effectively advance the search. Existing LLM-based methods typically rely on fixed allocation strategies throughout the search, potentially wasting resources on low-value candidates while overlooking promising ones. We propose EvoAlloc, a self-evolving resource-allocation agent that learns from search experience to revise its strategy for allocating computational resources across candidates. EvoAlloc periodically consolidates prior search and allocation outcomes into reusable experience, which informs subsequent strategy revisions. It further uses a counterfactual exploration mechanism to occasionally evaluate candidates denied resources by the allocator, revealing their outcomes to enrich its experience for future strategy updates. Across coding and agent-harness optimization benchmarks, EvoAlloc requires 59-82% fewer full evaluations and 61-89% fewer total LLM tokens to reach baseline-level performance. Moreover, under the same full-evaluation budget, EvoAlloc achieves 8.7-12.0% higher final performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.12086 — 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 2026-10-09T05:47:01.008Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).