Late Autumn: LLM Agents Specialize a General Multi-Robot Planner for One Warehouse
cs.RO, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- DeepFleet: Multi-Agent Foundation Models for Mobile Robots
- Local Guidance for Configuration-Based Multi-Agent Pathfinding
- Lifelong LaCAM with Local Guidance for Lifelong MAPF
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet
- Deadlock-Free Method for Multi-Agent Pickup and Delivery Problem Using Priority Inheritance with Temporary Priority
- MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
- ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
- Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding
- AIDE: AI-Driven Exploration in the Space of Code
- Idle Time Optimization for Target Assignment and Path Finding in Sortation Centers
- Alternating Target-Path Planning for Scalable Multi-Agent Coordination
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Optimal Target Assignment and Path Finding for Teams of Agents
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Engineering LaCAM$^\ast$: Towards Real-Time, Large-Scale, and Near-Optimal Multi-Agent Pathfinding
- AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
- CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation