Research map / Large language models / Agents, code and math
An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
Ni Zhang, Zhiguang Cao, Jianan Zhou, Cong Zhang, Yew-Soon Ong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase AFL solution-improvement iterations from 500 to 10000 (ablation) | AFL · CVRP n=100 | gap to HGS (%): 6.66 -> 2.38 | Improved |
| increase AFL iterations from 500 to 10000 (ablation) | AFL · CVRPTW n=100 | gap to HGS (%): 4.64 -> 1.46 | Improved |
| increase AFL iterations from 500 to 10000 (ablation) | AFL · CVRPL n=100 | gap to HGS (%): 10.08 -> 6.79 | Improved |
| AFL vs RF-POMO neural solver | AFL · CVRP n=100 | gap (%): 1.83 -> 2.38 | Hurt |
| AFL vs RF-POMO neural solver | AFL · CVRPTW n=100 | gap (%): 3.58 -> 1.46 | Improved |
| AFL vs HGS/OR-Tools on CVRPL (duration limit) | AFL · CVRPL n=100 | gap (%): 5.30 -> 6.79 | Hurt |
| AFL vs DRoC | AFL · TSPLib 500-1000 | gap (%): 4.22% -> 2.98% | Improved |
| AFL agentic framework vs DRoC code reliability | AFL · LLM-generated VRP code | runtime error rate: 82.4% -> 0% | Improved |
| remove judgment and revision agents (ablation) | AFL · problem description / code | validity | Improved |
Closest papers by meaning
- Rethinking Light Decoder-based Solvers for Vehicle Routing Problems (ICLR 2025 · similarity 0.86)
- MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem (NeurIPS 2025 · similarity 0.85)
- CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization (AAAI 2026 · similarity 0.85)
- EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions (ICML 2026 · similarity 0.85)
- PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (ICML 2026 · similarity 0.85)
- Fleet of Agents: Coordinated Problem Solving with Large Language Models (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
