# LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling

arXiv: https://arxiv.org/abs/2511.06260 · HTML: https://mlsanity.com/paper/2511.06260/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 86 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 21 of 21)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments](https://mlsanity.com/paper/2403.11807/) (2024)
- [Epidemic Modeling with Generative Agents](https://mlsanity.com/paper/2307.04986/) (2023)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [GAMEBoT: Transparent Assessment of LLM Reasoning in Games](https://mlsanity.com/paper/2412.13602/) (2024)
- ["Guinea Pig Trials" Utilizing GPT: A Novel Smart Agent-Based Modeling Approach for Studying Firm Competition and Collusion](https://mlsanity.com/paper/2308.10974/) (2023)
- [AI-Driven Day-to-Day Route Choice](https://mlsanity.com/paper/2412.03338/) (2024)
- [Large Language Models Playing Mixed Strategy Nash Equilibrium Games](https://mlsanity.com/paper/2406.10574/) (2024)
- [Playing games with Large language models: Randomness and strategy](https://mlsanity.com/paper/2503.02582/) (2025)
- [Aligning LLM with human travel choices: a persona-based embedding learning approach](https://mlsanity.com/paper/2505.19003/) (2025)
- [Can LLMs Understand Social Norms in Autonomous Driving Games?](https://mlsanity.com/paper/2408.12680/) (2024)
- [LLM-ABM for Transportation: Assessing the Potential of LLM Agents in System Analysis](https://mlsanity.com/paper/2503.22718/) (2025)
- [Explaining Puzzle Solutions in Natural Language: An Exploratory Study on 6x6 Sudoku](https://mlsanity.com/paper/2505.15993/) (2025)
- [Public Signals in Network Congestion Games](https://mlsanity.com/paper/2205.09823/) (2022)
- [Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games](https://mlsanity.com/paper/2407.04467/) (2024)
- [Wardrop Equilibrium Can Be Boundedly Rational: A New Behavioral Theory of Route Choice](https://mlsanity.com/paper/2304.02500/) (2023)
- [Value of Information in Bayesian Routing Games](https://mlsanity.com/paper/1808.10590/) (2018)
- [Information design in Bayesian routing games](https://mlsanity.com/paper/2309.06859/) (2023)
- [A Day-to-Day Dynamical Approach to the Most Likely User Equilibrium Problem](https://mlsanity.com/paper/2401.08013/) (2024)

## Built on by (most cited first, 2 of 2)

- [Thinking While Driving: A Concurrent Framework for Real-Time, LLM-Based Adaptive Routing](https://mlsanity.com/paper/2512.10610/) (2025)
- [AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?](https://mlsanity.com/paper/2606.13696/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models. Although more flexible and generalizable than conventional models, the practical use of these approaches remains limited by scalability due to the cost of calling one LLM for every traveler. Moreover, it has been found that LLM agents often make opaque choices and produce unstable day-to-day dynamics. To address these challenges, we propose to model each homogeneous traveler group facing the same decision context with a single representative LLM agent who behaves like the population's average, maintaining and updating a mixed strategy over routes that coincides with the group's aggregate flow proportions. Each day, the LLM reviews the travel experience and flags routes with positive reinforcement that they hope to use more often, and an interpretable update rule then converts this judgment into strategy adjustments using a tunable (progressively decaying) step size. The representative-agent design improves scalability, while the separation of reasoning from updating clarifies the decision logic while stabilizing learning. In classic traffic assignment settings, we find that the proposed approach converges rapidly to the user equilibrium. In richer settings with income heterogeneity, multi-criteria costs, and multi-modal choices, the generated dynamics remain stable and interpretable, reproducing plausible behavioral patterns well-documented in psychology and economics, for example, the decoy effect in toll versus non-toll road selection, and higher willingness-to-pay for convenience among higher-income travelers when choosing between driving, transit, and park-and-ride options.