arXiv:2607. 23676v1 Announce Type: new Abstract: LLM-based automated heuristic design (AHD) typically scores executable programs on complete instances or within fixed solver components.
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.
RouteRepair is a method that diagnoses specific weaknesses in large language model (LLM)-generated routing heuristics by evaluating performance at the instance level and then applies targeted modifications to the heuristic components that are failing, while preserving components that already perform well. It combines routing evidence, solver behavior, and program context to set bounded repair objectives and validates each change through matched parent-child evaluation of failure recovery and collateral degradation. Experiments on the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP) show significant reductions in optimality gaps and route costs, demonstrating that failure-aware, evidence-constrained refinement can improve routing heuristics on difficult instances while maintaining performance on easier cases.
arXiv:2608. 07544v1 Announce Type: cross Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs).
arXiv:2602. 23092v2 Announce Type: replace Abstract: The Capacitated Vehicle Routing Problem (CVRP), a fundamental combinatorial optimization challenge, focuses on optimizing fleet operations under vehicle capacity constraints.
arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is...
The paper introduces InFlowOp, a label‑free optimization framework that assigns costs to each decision in a multi‑agent workflow, balancing agent competence against execution time. It determines task granularity and agent assignment before execution and corrects faults during execution using the same cost metric. The authors also present Braid, a benchmark for multi‑agent coordination, and show that InFlowOp outperforms single‑agent baselines by up to 11.97% across various domains.
arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state h...