LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling

• URL: http://arxiv.org/abs/2511.06260v1
• Date: Sun, 09 Nov 2025 07:36:46 GMT
• Title: LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling
• Abstract summary: Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models.<n>We propose to model each homogeneous traveler group facing the same decision context with a single representative LLM agent.<n>We find that the proposed approach converges rapidly to the user equilibrium.
• Score: 2.8077601586229908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control [12.562136225497937]
  We propose a novel learning paradigm named LATS that integrates Large Language Models (LLMs) and Multi-agent Reinforcement Learning (MARL)<n>LLMs excel at semantic representation, reasoning, and analysis, yet their propensity for hallucination and slow inference speeds often hinder their direct application to decision-making tasks.<n>A trained embedding LLM serves as a teacher to generate rich semantic features that capture each intersection's topology structures and traffic dynamics.
  arXiv  Detail & Related papers  (2026-03-25T14:42:32Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Directional Reasoning Injection for Fine-Tuning MLLMs [51.53222423215055]
  Multimodal large language models (MLLMs) are rapidly advancing, yet their reasoning ability often lags behind that of strong text-only counterparts.<n>Existing methods to bridge this gap rely on supervised fine-tuning over large-scale multimodal reasoning data or reinforcement learning.<n>We propose Directional Reasoning Injection for Fine-Tuning (DRIFT) to solve this problem.
  arXiv  Detail & Related papers  (2025-10-16T18:06:46Z)
• Addressing the alignment problem in transportation policy making: an LLM approach [0.3499870393443268]
  A key challenge in transportation planning is that the collective preferences of heterogeneous travelers often diverge from the policies produced by model-driven decision tools.<n>Here, we investigate whether large language models (LLMs) can help inform and address this alignment problem.
  arXiv  Detail & Related papers  (2025-10-15T04:36:38Z)
• Synthesizing Attitudes, Predicting Actions (SAPA): Behavioral Theory-Guided LLMs for Ridesourcing Mode Choice Modeling [4.901179513819295]
  Existing models for predicting ridesourcing mode choices often suffer from limited predictive accuracy due to their inability to capture key psychological factors.<n>This paper introduces the Synthesizing Attitudes, Predicting Actions (SAPA) framework to synthesize theory-grounded latent attitudes.<n> Experiments on a large-scale, multi-year travel survey show that SAPA significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-09-18T01:52:27Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systems [5.5597941107270215]
  We introduce Multi-Residual Mixture of Expert Learning (MRMEL) for Lagrangian traffic control.<n>MRMEL augments a suboptimal nominal AV control policy by learning a residual correction.<n>We validate MRMEL using a case study in cooperative eco-driving at signalized intersections in Atlanta, Dallas Fort Worth, and Salt Lake City.
  arXiv  Detail & Related papers  (2025-07-14T00:17:12Z)
• Aligning LLM with human travel choices: a persona-based embedding learning approach [15.11130742093296]
  This paper introduces a novel framework for aligning large language models with human travel choice behavior.<n>Our framework uses a persona inference and loading process to condition LLMs with suitable prompts to enhance alignment.
  arXiv  Detail & Related papers  (2025-05-25T06:54:01Z)
• Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning [69.5875073447454]
  This paper advances motion agents empowered by large language models (LLMs) toward autonomous navigation in dynamic and cluttered environments.<n>Our training-free framework supports multi-agent coordination, closed-loop replanning, and dynamic obstacle avoidance without retraining or fine-tuning.
  arXiv  Detail & Related papers  (2025-03-10T13:39:09Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• AI-Driven Day-to-Day Route Choice [15.934133434324755]
  "LLMTraveler" is an agent that learns from past experiences and makes decisions by balancing retrieved data and personality traits.<n>This paper systematically evaluates the LLMTraveler's ability to replicate human-like decision-making through two stages of day-to-day congestion games.<n>This capability offers valuable insights for transportation policymaking, such as simulating traveler responses to new policies or changes in the network.
  arXiv  Detail & Related papers  (2024-12-04T14:13:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.