mlsanityData to 7 Oct 2026

Where You Go is Who You Are: Behavioral Theory-Guided LLMs for Inverse Reinforcement Learning

arXiv 2505.17249 ↗First posted 22 May 2025cs.AI cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Imitation and offline RL for driving

Abstract (arXiv)

Big trajectory data hold great promise for human mobility analysis, but their utility is often constrained by the absence of critical traveler attributes, particularly sociodemographic information. While prior studies have explored predicting such attributes from mobility patterns, they often overlooked underlying cognitive mechanisms and exhibited low predictive accuracy. This study introduces SILIC, short for Sociodemographic Inference with LLM-guided Inverse Reinforcement Learning (IRL) and Cognitive Chain Reasoning (CCR), a theoretically grounded framework that leverages LLMs to infer sociodemographic attributes from observed mobility patterns by capturing latent behavioral intentions and reasoning through psychological constructs. Particularly, our approach explicitly follows the Theory of Planned Behavior (TPB), a foundational behavioral framework in transportation research, to model individuals' latent cognitive processes underlying travel decision-making. The LLMs further provide heuristic guidance to improve IRL reward function initialization and update by addressing its ill-posedness and optimization challenges arising from the vast and unstructured reward space. Evaluated in the 2017 Puget Sound Regional Council Household Travel Survey, our method substantially outperforms state-of-the-art baselines and shows great promise for enriching big trajectory data to support more behaviorally grounded applications in transportation planning and beyond.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation and offline RL for driving, one of 13 directions in Offline RL and imitation learning from data. Builds on 15 of its 56 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

15 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewards18 Jun

Other references · 14

  1. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 176
  2. 2023Understanding Social Reasoning in Language Models with Language Modelscited by 166
  3. 2020A Survey on Deep Learning for Human Mobilitycited by 87
  4. 2021Identifiability in inverse reinforcement learningcited by 55
  5. 2024SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMscited by 51
  6. 2024Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpuscited by 32
  7. 2025Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptionscited by 31
  8. 2024Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysiscited by 30
  9. 2024Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learningcited by 27
  10. 2025Thinking Machines: A Survey of LLM based Reasoning Strategiescited by 25
  11. 2025From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMscited by 12
  12. 2024Predicting and Understanding Human Action Decisions: Insights from Large Language Models and Cognitive Instance-Based Learningcited by 8
2 more
  1. 2021Estimating Wildfire Evacuation Decision and Departure Timing Using Large-Scale GPS Datacited by 5
  2. 2024From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledgecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs
  2. 2024Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles
  3. 2026Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems
  4. 2025Analyzing sequential activity and travel decisions with interpretable deep inverse reinforcement learning
  5. 2025Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
  6. 2025Deep Generative Model for Human Mobility Behavior
  7. 2025Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
  8. 2026An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction