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

TL;DR

This paper introduces a real-time, LLM-based adaptive routing framework for driving that enables agents to plan routes dynamically while moving, reducing wait times and improving traffic flow in a shared environment.

Contribution

It presents a novel concurrent routing system integrating LLMs with a real-time traffic environment, enabling dynamic, adaptive route planning without stopping.

Findings

Agents achieve an average decision latency of 0.75 seconds under high traffic.

LLM-driven agents can reroute dynamically around congestion.

The framework supports real-time multi-agent coordination in traffic environments.

Abstract

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.