{"slug": "routerepair-instance-level-failure-diagnosis-and-targeted-repair-in-llm-based", "title": "RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization", "summary": "A study posted to arXiv (2609.11452v1) introduces RouteRepair, an instance-level failure diagnosis and targeted repair method for LLM-based automated heuristic design in routing optimization. On the traveling salesman problem, RouteRepair-GLS cut the mean optimality gap from 1.7476% to 0.7587%, and on the capacitated vehicle routing problem a constructive heuristic lowered average route cost by 1.91% versus the savings heuristic, with generated ant colony optimization priors also beating matched hand-designed priors. The authors report that failure-aware, evidence-constrained refinement improves routing heuristics on difficult instances while preserving performance on cases already solved well.", "body_md": "arXiv:2609.11452v1 Announce Type: new \nAbstract: Efficient routing optimization is essential to freight transportation, urban logistics, and shared mobility, where high-quality heuristics are often required under limited computational budgets. Recent large language model (LLM)-based automated heuristic design methods can generate effective routing rules, but aggregate evaluation may mask recurrent failures on particular instance structures. To address this limitation, this study develops RouteRepair, which diagnoses parent-specific weaknesses from instance-level performance and applies targeted modifications to the corresponding heuristic components while protecting behavior that already performs well. Routing evidence, solver behavior, and program context are combined to define bounded repair objectives, and each intervention is validated through matched parent-child evaluation of failure recovery and collateral degradation. Experiments on the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP) span constructive search, guided local search, and ant colony optimization. RouteRepair-GLS reduces the mean TSP optimality gap from 1.7476% to 0.7587%, while the constructive CVRP heuristic lowers average route cost by 1.91% relative to the savings heuristic; the generated ACO priors also outperform matched hand-designed priors. These results show that failure-aware, evidence-constrained refinement can improve routing heuristics on difficult instances while preserving performance on cases they already solve well.", "url": "https://wpnews.pro/news/routerepair-instance-level-failure-diagnosis-and-targeted-repair-in-llm-based", "canonical_source": "https://www.machinebrief.com/news/routerepair-instance-level-failure-diagnosis-and-targeted-re-36ph", "published_at": "2026-09-12 04:00:00+00:00", "updated_at": "2026-09-12 04:28:16.201671+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "machine-learning"], "entities": ["RouteRepair", "RouteRepair-GLS", "arXiv", "traveling salesman problem", "capacitated vehicle routing problem", "ant colony optimization", "guided local search"], "alternates": {"html": "https://wpnews.pro/news/routerepair-instance-level-failure-diagnosis-and-targeted-repair-in-llm-based", "markdown": "https://wpnews.pro/news/routerepair-instance-level-failure-diagnosis-and-targeted-repair-in-llm-based.md", "text": "https://wpnews.pro/news/routerepair-instance-level-failure-diagnosis-and-targeted-repair-in-llm-based.txt", "jsonld": "https://wpnews.pro/news/routerepair-instance-level-failure-diagnosis-and-targeted-repair-in-llm-based.jsonld"}}