Small Agents, Big Gains: Journey-Aware and Critic-Guided Simulation for Long-Horizon Shopping Dialogues
TL;DR
This work proposes a closed-loop Multi-Agent Simulation Framework to synthe-size diverse, faithful, and policy-aligned shopping trajectories, and presents synthetic data that enables a small model to significantly outperform same-size baselines and surpass a large-model baseline.
Abstract
Modern e-commerce assistants must go beyond simple product search to support inspiration, comparison, and tool-grounded fact-checking across non-linear shopping journeys. However, distilling these complex behaviors into efficient, deployable models is bottle-necked by a lack of post-training data: trajectories must cover diverse agentic workflows with high fidelity, yet the desired outputs are open-ended without a single ground truth. We propose a closed-loop Multi-Agent Simulation Framework to synthe-size diverse, faithful, and policy-aligned shopping trajectories. The system orchestrates a journey-aware, stateful user simulator to drive exploration, a shopping agent that manages both tools and UI elements, and a critic agent that provides rubric-driven feedback to iteratively refine the data. On a domain-specific benchmark, this synthetic data enables a small model to significantly outperform same-size baselines and surpass a large-model baseline, making it viable to deploy the smaller back-bone at 8 × higher inference throughput than the large baseline.