Aligning LLM agents with human learning and adjustment behavior: a dual agent approach

TL;DR

This paper presents a dual-agent framework using LLMs to simulate and align with human travelers' learning and adaptation behaviors, improving accuracy and realism in transportation modeling.

Contribution

Introduces a novel dual-agent LLM framework with calibration for realistic, adaptive traveler simulation, advancing beyond simple mimicry to underlying behavioral alignment.

Findings

Outperforms existing LLM-based methods in behavioral alignment

Achieves higher accuracy in individual and aggregate travel behavior simulations

Captures evolution of learning processes for deeper behavioral realism

Abstract

Effective modeling of how human travelers learn and adjust their travel behavior from interacting with transportation systems is critical for system assessment and planning. However, this task is also difficult due to the complex cognition and decision-making involved in such behavior. Recent research has begun to leverage Large Language Model (LLM) agents for this task. Building on this, we introduce a novel dual-agent framework that enables continuous learning and alignment between LLM agents and human travelers on learning and adaptation behavior from online data streams. Our approach involves a set of LLM traveler agents, equipped with a memory system and a learnable persona, which serve as simulators for human travelers. To ensure behavioral alignment, we introduce an LLM calibration agent that leverages the reasoning and analytical capabilities of LLMs to train the personas of these traveler agents. Working together, this dual-agent system is designed to track and align the underlying decision-making mechanisms of travelers and produce realistic, adaptive simulations. Using a real-world dataset from a day-to-day route choice experiment, we show our approach significantly outperforms existing LLM-based methods in both individual behavioral alignment and aggregate simulation accuracy. Furthermore, we demonstrate that our method moves beyond simple behavioral mimicry to capture the evolution of underlying learning processes, a deeper alignment that fosters robust generalization. Overall, our framework provides a new approach for creating adaptive and behaviorally realistic agents to simulate travelers' learning and adaptation that can benefit transportation simulation and policy analysis.