Metraipolis › archive › dc_a5628dacfdce
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search — arXiv:2608.15546
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15546
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:25:13.255Z
- SHA-256 of the archived text
7999f410e6451ae2f8f498fbe9335cb2aacef3ae41511bba874081c6e15cbc8f- Stable URL of this page
https://metraipolis.com/documento/dc_a5628dacfdce
How to cite
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search — arXiv:2608.15546 — arXiv (en), https://arxiv.org/abs/2608.15546 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5628dacfdce (Metraipolis archive dc_a5628dacfdce, sha256 7999f410e6451ae2f8f498fbe9335cb2aacef3ae41511bba874081c6e15cbc8f)
BibTeX
@misc{dca5628dacfdce,
title = {ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search — arXiv:2608.15546},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15546},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5628dacfdce; sha256 7999f410e6451ae2f8f498fbe9335cb2aacef3ae41511bba874081c6e15cbc8f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15546. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most LLM-based automated algorithm design methods optimize a designated component within a human-specified scaffold, fixing overall organization and component interactions. We present ATLAS, an embedding-guided quality-diversity framework for scaffold-free full-algorithm synthesis in combinatorial optimization. The problem specification supplies objectives and constraints; a minimal I/O interface fixes only instance and solution formats; the LLM chooses and restructures components, interactions, and control flow. This freedom enlarges the search space, risking invalid candidates and premature convergence to one design region. ATLAS independently detects execution, interface, and feasibility failures, recomputes objectives, and applies error-conditioned repair; similarity-based archive management preserves algorithms across embedding-space regions to counter premature convergence. Its three-layer search refines the best design, gives other regions dedicated refinement opportunities, and performs cross-region synthesis to recombine components and their interactions. Across four NP-hard problems, ATLAS outperforms several state-of-the-art component-synthesis methods and a matched full-synthesis baseline while remaining competitive with strong human-designed algorithms. One ATLAS run retains several algorithms with comparable performance from distinct embedding-space regions rather than a single design. Code inspection finds that these multi-component designs differ in their primary construction or global-search backbone. Our results suggest that embedding-guided quality-diversity search can make the enlarged full-algorithm design space practically searchable. Source code and exact executable prompts are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2608.15546 — 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 2026-10-18T16:29:13.809Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).