ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning

TL;DR

This paper introduces ChatShopBuddy, a reinforcement learning framework for conversational shopping agents that optimizes multiple objectives, using a new benchmark, hierarchical reward modeling, and dynamic policy optimization to improve response quality and efficiency.

Contribution

It presents a comprehensive methodology including a new benchmark, hierarchical reward modeling, and dynamic policy optimization for training reliable conversational shopping agents.

Findings

RL-trained ChatShopBuddy outperforms larger models in stability.

The hierarchical reward model effectively captures complex quality requirements.

Dynamic contrastive policy optimization balances response quality and operational efficiency.

Abstract

Conversational shopping agents represent a critical consumer-facing application of Large Language Model (LLM)-powered agents, yet how to effectively apply post-training Reinforcement Learning (RL) to optimize such agents remains underexplored. This work investigates RL-based optimization for shopping agents in real-world scenarios, where agents must simultaneously satisfy multiple interdependent objectives spanning objective metrics (product correctness), subjective qualities (persuasiveness), outcome rewards (final response quality), and process rewards (tool efficiency). We present a complete methodology to address this challenge. Specifically, we first construct SmartShopBench, a benchmark that captures diverse shopping intents with a hierarchical evaluation that decomposes complex quality requirements into measurable levels. Building on this evaluation framework, we design Hierarchical Reward Modeling (HRM) to structure mixed reward types through conditional gating that reflects their logical dependencies. To enable efficient training, we further propose Dynamic Contrastive Policy Optimization (DCPO), which balances response quality with operational efficiency through dynamic trajectory selection based on reward and reasoning length. Extensive experiments demonstrate that our RL-trained agent, namely ChatShopBuddy, consistently outperforms larger models relying on generic reasoning, achieving superior stability rather than merely higher peaks. Our work provides valuable guidance for applying RL to real-world conversational agents.