ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search

ATLAS is an embedding‑guided quality‑diversity framework that enables scaffold‑free synthesis of full algorithms for combinatorial optimization using large language models. It allows the LLM to freely choose, restructure, and control algorithm components while automatically detecting and repairing execution, interface, and feasibility failures. Across four NP‑hard problems, ATLAS outperforms state‑of‑the‑art component‑synthesis methods and remains competitive with strong human‑designed algorithms, demonstrating that a larger design space can be practically searched.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• rag
• benchmarks