用多智能体分工提升游戏推荐对话的安全与个性化。
Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition
- 分设意图解析、检索、排序等专用智能体，协同完成推荐
- 在真实数据上提升命中率20%，降低流行度偏差24%
- 适合关注安全与用户对齐的游戏推荐系统研究者
对话式推荐系统（CRS）借助大语言模型在电影等领域取得显著进展，但游戏场景面临动态内容更新、以交互为导向的偏好（如技能水平、操作机制、硬件要求）及开放对话中潜在的不安全回复风险。本文提出MATCHA框架，采用多智能体分解结构，分配专门智能体负责意图解析、工具增强检索、多大模型排序（含反思、解释与风险控制），实现更精细的个性化、长尾内容覆盖与更强安全性。在真实用户请求数据集上评估，MATCHA在8项指标上优于6个基线，命中率（Hit@5）提升20%，流行度偏差降低24%，对抗攻击防御率达97.9%。人工与虚拟评审均证实其解释质量与用户对齐性显著提升。
原文摘要 · Abstract (English)
Conversational recommender systems (CRS) have advanced with large language models, showing strong results in domains like movies. These domains typically involve fixed content and passive consumption, where user preferences can be matched by genre or theme. In contrast, games present distinct challenges: fast-evolving catalogs, interaction-driven preferences (e.g., skill level, mechanics, hardware), and increased risk of unsafe responses in open-ended conversation. We propose MATCHA, a multi-agent framework for CRS that assigns specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking with reflection, explanation, and risk control which enabling finer personalization, long-tail coverage, and stronger safety. Evaluated on real user request dataset, MATCHA outperforms six baselines across eight metrics, improving Hit@5 by 20%, reducing popularity bias by 24%, and achieving 97.9% adversarial defense. Human and virtual-judge evaluations confirm improved explanation quality and user alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。