SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection

TL;DR

SimRPD is a three-stage framework that enhances recruitment dialogue agents by using a high-fidelity simulator, a comprehensive evaluation method, and data selection to improve training quality and performance.

Contribution

The paper introduces a novel multi-stage approach combining a user simulator, a Chain-of-Intention evaluation framework, and data selection to improve goal-oriented dialogue agent training.

Findings

SimRPD outperforms existing data selection strategies in recruitment scenarios.

The high-fidelity simulator effectively generates large-scale conversational data.

The evaluation framework ensures high-quality data selection for training.

Abstract

Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcomes, such as acquiring social-media contacts for private-channel conversion. Although supervised fine-tuning and reinforcement learning have proven effective for training such agents, their performance is heavily constrained by the scarcity of high-quality, goal-oriented domain-specific training data. To address this challenge, we propose SimRPD, a three-stage framework for training recruitment proactive dialogue agents. First, we develop a high-fidelity user simulator to synthesize large-scale conversational data through multi-turn online dialogue. Then we introduce a multi-dimensional evaluation framework based on Chain-of-Intention (CoI) to comprehensively assess the simulator and effectively select high-quality data, incorporating both global-level and instance-level metrics. Finally, we train the recruitment proactive dialogue agent on the selected dataset. Experiments in a real-world recruitment scenario demonstrate that SimRPD outperforms existing simulator-based data selection strategies, highlighting its practical value for industrial deployment and its potential applicability to other business-oriented dialogue scenarios.