{
  "id": 5133,
  "url": "https://arxiv.org/abs/2605.00370v2",
  "title": "Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration",
  "summary": "Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose Group Cognition Learning (GCL), a governed ",
  "authors": "Chunlei Meng, Pengbin Feng, Rong Fu, Hoi Leong Lee, Xiaojing Du, Zhaolu Kang et al.",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-01T03:19:34.000Z",
  "fetched_at": "2026-07-14T16:31:31.212Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5133",
  "original_url": "https://arxiv.org/abs/2605.00370v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}