MAPS: Modeling Co-Existing Subjective Perspectives and Shared Meaning in Multi-Agent Cognitive Dialogue

Researchers introduced MAPS (Multi-Agent Perspective Spaces), a framework for multi-agent dialogue that models distinct cognitive perspectives while enabling convergence on shared meaning. Using domain-weighted profiles, GRU-based memory, and token-level attention, MAPS outperformed baselines on EmpatheticDialogues, TopicalChat, and MultiWOZ, balancing semantic alignment with subjective diversity. The work advances cognitively grounded, interpretable AI dialogue systems.

arXiv:2607.14110v1 Announce Type: new Abstract: Human dialogue involves more than exchanging information; it also expresses beliefs, emotions, and subjective cognitive styles. Yet current AI dialogue systems often enforce semantic uniformity, sacrificing diversity and interpretability. We present MAPS Multi-Agent Perspective Spaces , a novel framework that models dialogue between cognitively distinct agents through domain-weighted profiles, dynamic GRU-based memory, and interpretable token-level attention. MAPS enables agents to maintain individualized reasoning while progressively converging on shared meaning. Evaluations on EmpatheticDialogues, TopicalChat, and MultiWOZ show that MAPS supports semantic alignment without collapsing subjectivity. Our results demonstrate a path toward cognitively grounded, interpretable dialogue systems that balance expressiveness and coherence.