Thinking While Driving: A Concurrent Framework for Real-Time, LLM-Based Adaptive Routing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Xiaopei, Fan, Muyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914195112460288
author Tan, Xiaopei
Fan, Muyang
author_facet Tan, Xiaopei
Fan, Muyang
contents We present Thinking While Driving, a concurrent routing framework that integrates LLMs into a graph-based traffic environment. Unlike approaches that require agents to stop and deliberate, our system enables LLM-based route planning while agents are moving, significantly reducing intersection wait times. Under high traffic, agents average just 0.75 seconds of decision latency. To coordinate many agents in real-time, we implement a non-blocking asynchronous architecture using Unity coroutines and a dedicated request manager. The environment is a weighted undirected graph with live congestion metrics, updated continuously by the agents to enable shared perception. Our results show LLM-driven agents can dynamically adapt to traffic, reroute around congestion, and exhibit behaviors beyond static pathfinding, all while maintaining real-time performance. This work provides a reproducible framework for future research in adaptive routing and multi-agent cooperation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10610
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thinking While Driving: A Concurrent Framework for Real-Time, LLM-Based Adaptive Routing
Tan, Xiaopei
Fan, Muyang
Multiagent Systems
We present Thinking While Driving, a concurrent routing framework that integrates LLMs into a graph-based traffic environment. Unlike approaches that require agents to stop and deliberate, our system enables LLM-based route planning while agents are moving, significantly reducing intersection wait times. Under high traffic, agents average just 0.75 seconds of decision latency. To coordinate many agents in real-time, we implement a non-blocking asynchronous architecture using Unity coroutines and a dedicated request manager. The environment is a weighted undirected graph with live congestion metrics, updated continuously by the agents to enable shared perception. Our results show LLM-driven agents can dynamically adapt to traffic, reroute around congestion, and exhibit behaviors beyond static pathfinding, all while maintaining real-time performance. This work provides a reproducible framework for future research in adaptive routing and multi-agent cooperation.
title Thinking While Driving: A Concurrent Framework for Real-Time, LLM-Based Adaptive Routing
topic Multiagent Systems
url https://arxiv.org/abs/2512.10610