AI Paper Atlas

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

ICLR 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 9 citations (OpenAlex)

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 changedWhereMeasuredEffect
increase AFL solution-improvement iterations from 500 to 10000 (ablation)AFL · CVRP n=100gap to HGS (%): 6.66 -> 2.38Improved
increase AFL iterations from 500 to 10000 (ablation)AFL · CVRPTW n=100gap to HGS (%): 4.64 -> 1.46Improved
increase AFL iterations from 500 to 10000 (ablation)AFL · CVRPL n=100gap to HGS (%): 10.08 -> 6.79Improved
AFL vs RF-POMO neural solverAFL · CVRP n=100gap (%): 1.83 -> 2.38Hurt
AFL vs RF-POMO neural solverAFL · CVRPTW n=100gap (%): 3.58 -> 1.46Improved
AFL vs HGS/OR-Tools on CVRPL (duration limit)AFL · CVRPL n=100gap (%): 5.30 -> 6.79Hurt
AFL vs DRoCAFL · TSPLib 500-1000gap (%): 4.22% -> 2.98%Improved
AFL agentic framework vs DRoC code reliabilityAFL · LLM-generated VRP coderuntime error rate: 82.4% -> 0%Improved
remove judgment and revision agents (ablation)AFL · problem description / codevalidityImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy