Metraipolis › archive › dc_70a154fbca21

HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization — arXiv:2609.36303

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36303
License (as archived)
CC0-1.0
Archived
2026-10-07T16:56:29.654Z
SHA-256 of the archived text
d04daa20d6d1c4c462c30b1f25d35c0135f8e75e4dbe8f7a22e6d9b4533abcd3
Stable URL of this page
https://metraipolis.com/documento/dc_70a154fbca21

How to cite

HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization — arXiv:2609.36303 — arXiv (en), https://arxiv.org/abs/2609.36303 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70a154fbca21 (Metraipolis archive dc_70a154fbca21, sha256 d04daa20d6d1c4c462c30b1f25d35c0135f8e75e4dbe8f7a22e6d9b4533abcd3)
BibTeX
@misc{dc70a154fbca21,
  title = {HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization — arXiv:2609.36303},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36303},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70a154fbca21; sha256 d04daa20d6d1c4c462c30b1f25d35c0135f8e75e4dbe8f7a22e6d9b4533abcd3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36303. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in agentic heuristic design use AI agents and execution feedback to automate algorithm discovery for challenging optimization problems. In many practical settings, high-quality solutions must be obtained under strict runtime constraints, motivating hybrid approaches that combine problem-specific heuristics with powerful mathematical programming solvers. However, existing approaches typically improve heuristic components within predefined procedures or tune solver configurations in isolation. This limits holistic adaptation of where to allocate computation, how to leverage solvers, and how to refine the overall algorithmic structure. To address these limitations, we propose HeurEvo, an automated plan--code--component co-evolution framework that jointly evolves the high-level algorithmic structures, their implementations, and a shared pool of reusable components. A planner determines which algorithmic components to use, how to combine them, and how to allocate runtime across stages, a coder realizes the resulting plan as executable code, while a component evolver updates the shared component pool. Within an island-based evolutionary framework, plans and implementations co-evolve with feedback from an interpreter agent that analyzes execution results and identifies opportunities for improvement. Across diverse combinatorial optimization benchmarks and challenging MIPLIB instances, HeurEvo finds high-quality solutions within tight runtime budgets, often matching or surpassing state-of-the-art optimization solvers given hours or days of computation. On several nonlinear geometry problems such as hexagon packing, it also improves upon the best previously reported results. These results highlight the value of jointly searching over algorithmic structure and implementation for agentic heuristic design.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.36303 — 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 2026-10-07T16:27:03.198Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).