解决多智能体对话中身份模糊和重复啰嗦问题，让角色更鲜明、协作更高效。
MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems
- 分层优化：先个性化每个智能体身份，再整体协调对话多样性
- 身份一致性提升14.1，社交贡献度提高10.6，显著减少冗余对话
- 适合做情感陪伴、协同创作的多角色对话系统开发者参考
多智能体系统（MAS）正成为提供情感与认知支持的潜在社会协作伙伴。然而，现有系统常出现身份坍缩（即智能体退化为通用助手行为）和社会迎合（即产生冗余、无建设性的对话）。本文提出 MASCOT，一种面向多视角社会协作伴侣的多智能体框架。MASCOT 采用新颖的双层优化策略：1）基于 RLAIF 的个性感知行为对齐，微调各智能体以形成独特身份；2）协作对话优化，通过群体级调整促进互补、多样且富有成效的对话。我们在涵盖域内与域外（OOD）设置的人类基准场景中评估 MASCOT，相比先进基线，其在身份一致性上最高提升 +14.1，在社会贡献度上最高提升 +10.6。全面评估包括人工评价、多个 LLM 判官、三路对比及自动指标，结果表明 MASCOT 能生成更角色一致、更少冗余的多智能体对话。
原文摘要 · Abstract (English)
Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona collapse, where agents revert to generic, homogenized assistant behaviors, and social sycophancy, where agents produce redundant, non-constructive dialogue. We propose MASCOT, a multi-agent framework for multi-perspective socio-collaborative companions. MASCOT introduces a novel bi-level optimization strategy to harmonize individual and collective behaviors: 1) Persona-Aware Behavioral Alignment, an RLAIF-driven pipeline that fine-tunes individual agents for agent-specific identities; and 2) Collaborative Dialogue Optimization, a group-level adaptation process that promotes complementary, diverse, and productive discourse. We evaluate MASCOT using human-grounded contexts drawn across both in-domain and out-of-domain (OOD) settings against state-of-the-art baselines. MASCOT improves persona consistency by up to +14.1 and social contribution by up to +10.6. A broad evaluation suite, including human evaluation, multiple LLM judges, three-way comparisons, and automatic metrics, further shows that MASCOT produces more role-consistent and less redundant multi-agent dialogue.
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。