Metraipolis › archive › dc_033ed6b261ae

MAPLE: Memory-Augmented Planning with Language and Evolution — arXiv:2609.11636

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11636
License (as archived): CC0-1.0
Archived: 2026-10-16T05:24:28.276Z
SHA-256 of the archived text: 06d660a61186a9d30f86f1134a27c02e60f7e04b784bc06410e874b595e5106b
Stable URL of this page: https://metraipolis.com/documento/dc_033ed6b261ae

How to cite

MAPLE: Memory-Augmented Planning with Language and Evolution — arXiv:2609.11636 — arXiv (en), https://arxiv.org/abs/2609.11636 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_033ed6b261ae (Metraipolis archive dc_033ed6b261ae, sha256 06d660a61186a9d30f86f1134a27c02e60f7e04b784bc06410e874b595e5106b)

BibTeX

@misc{dc033ed6b261ae,
  title = {MAPLE: Memory-Augmented Planning with Language and Evolution — arXiv:2609.11636},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11636},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_033ed6b261ae; sha256 06d660a61186a9d30f86f1134a27c02e60f7e04b784bc06410e874b595e5106b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11636. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agents translate natural-language requirements into models or solver programs that established optimization tools can execute. This progress makes optimization more accessible, but real-world operations are dynamic: changing demand, resources, and priorities require updates to data, constraints, and objectives. Methods centered on isolated requests offer limited support for rapid adaptation that preserves earlier decisions and reuses useful search results. We introduce MAPLE (Memory-Augmented Planning with Language and Evolution), an agent for maintaining optimization problems through successive natural-language requests. MAPLE combines language-based problem construction with mathematical programming and evolutionary search. It retains the optimization program, accepted plans, earlier updates, and candidate solutions for subsequent requests. We introduce NLDO, a benchmark of 15 trajectories and 180 updates spanning selection, scheduling, rostering, routing, and cloud-resource placement. In the main evaluation, MAPLE completes all trajectories and achieves online scalar quality of 0.951 and a Pareto hypervolume ratio of 0.875. Controlled comparisons further show that maintaining executable state improves update validity and can preserve useful search information across substantial revisions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.11636 — 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 2026-10-16T05:17:52.042Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).