AI RESEARCH
ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback
arXiv CS.AI
•
ArXi:2604.04940v1 Announce Type: new Designing effective heuristics for NP-hard combinatorial optimization problems remains a challenging and expertise-intensive task. Existing applications of large language models (LLMs) primarily rely on one-shot code synthesis, yielding brittle heuristics that underutilize the models' capacity for iterative reasoning. We propose ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback, a hybrid framework that embeds LLMs as interactive, multi-turn reasoners within an evolutionary algorithm (EA.