Skip to content
Review

Late Autumn: LLM Agents Specialize a General Multi-Robot Planner for One Warehouse

Nov 2026 · 0 citations · 35 references
Computer Science

TL;DR

This work studies six campaigns on a lifelong planner that combines task assignment with multi-agent path finding, on a floor modeled on an existing automated warehouse, and finds that LLM agents can turn each site's bias into extra throughput at little engineering cost, with reviewable patches.

Abstract

No algorithm is best on all problems, but a real warehouse is a narrow problem: its layout and processes rarely change. Operators still run one general multi-robot planner at many sites, because experts cannot tune it for each one. In this work, which we call Late Autumn, we explore whether LLM coding agents running autonomous research can specialize a general planner for one site, trading generality for throughput, much as post-training adapts a pretrained LLM to one task. We study six campaigns on a lifelong planner that combines task assignment with multi-agent path finding, on a floor modeled on an existing automated warehouse. We find that (1) the agents raise throughput by 22--60%, and the gains hold on unseen seeds; (2) they rediscover known MAPF mechanisms, such as corridor-exit priorities, local guidance, and rollouts, and independent campaigns find the same bottleneck; (3) the gains largely carry over to another layout, a larger fleet, and other service times, shrink with a smaller fleet, and mostly vanish under an outbound-heavy demand mix; and (4) each final patch (0.7k--2.4k lines) is a chain of scored commits with a median step of 27 lines, so experts can review it, and review finds problems that the score misses; some patches multiply planner compute by over 100x. LLM agents can therefore turn each site's bias into extra throughput at little engineering cost, with reviewable patches; we expect experts to shift toward designing insightful metrics and fast simulators that mirror the real problem.

View source

Similar papers

Preprint Nov 2026

Local Solution Repair for Multi-Agent Pickup and Delivery

Multi-robot systems in automated warehouses must efficiently attend to a constant stream of pickup-and-delivery tasks while avoiding collisions. Existing Multi-Agent Pickup-and-Delivery (MAPD) solutions generate plans that are globally feasible but often locally inefficient. In large-scale, long-horizon deployments, th...

Ethan Schneider, Jing-Kai Chen, Seth Hutchinson et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Policy Search in Code Space for Multi-Agent Pathfinding

This work investigates a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification and shows that this workflow robustly outperformed any manually engineered solutions.

Matthias Eder, Pantelis Emmanouil, V. Farias et al. · 0 citations
Sep 2026

Solving Multi-Agent Sokoban via LaCAM

Sokoban, a puzzle game in which an agent pushes boxes onto unlabelled target locations in a grid world, is a long-standing benchmark planning problem. While it is easy to see the connection to practical applications such as warehouse logistics with autonomous forklifts, its multi-agent counterpart has remained underdev...

Keisuke Okumura · 0 citations

Planner-as-Router: Joint Plan-Time Model Routing for Cost-Efficient Multi-Agent Workflows

PaR stays on the observed cost-accuracy frontier, matches a sink-frontier heuristic in accuracy at comparable cost and a faithful FrugalGPT cascade at lower cost, and cuts cost 44% against all-frontier routing while giving up 2.9 points of accuracy.

V. Singh, Preeti Priyam, Gautam Bhowmick · 0 citations
#artificial intelligence Preprint Nov 2026

EnvOpt: Automated Optimization for Agent Environments

Results show that how information is represented to an agent shapes both its cost and its success, making the environment worth optimizing in addition to the parameters and the harness, making the environment worth optimizing in addition to the parameters and the harness.

Ming-Xuan Li, Huan-Zhi Mao, Qiu-Yang Mang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.