https://ahren09.github.io/tags/emotional-support/Emotional SupportHugo Blox Builder (https://hugoblox.com)en-usWed, 01 Jul 2026 00:00:00 +0000https://ahren09.github.io/media/icon_hu_eee6347cbdb2cc3f.pnghttps://ahren09.github.io/tags/emotional-support/https://ahren09.github.io/publication/emnlp26_mascot/Wed, 01 Jul 2026 00:00:00 +0000https://ahren09.github.io/publication/emnlp26_mascot/<h2 id="abstract">Abstract</h2> <p>Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from <em>persona collapse</em>, where agents revert to generic, homogenized assistant behaviors, and <em>social sycophancy</em>, 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) <strong>Persona-Aware Behavioral Alignment</strong>, an RLAIF-driven pipeline that finetunes individual agents for agent-specific identities; and (2) <strong>Collaborative Dialogue Optimization</strong>, 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.</p>