Replaces unstructured LLM debates with 'Deliberative Collective Intelligence,' producing formal decision packets with minority reports and accountability trails.
arXiv · March 13, 2026 · 2603.11781
Why it matters
It moves multi-agent reasoning from simple voting or chat-based consensus to a structured protocol with 14 typed epistemic acts. This is a critical advancement for enterprise and high-stakes AI deployment where the 'why' (including residual objections) is as valuable as the decision itself.
From the abstract
Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration. None model deliberation: a phased process where differentiated participants exchange typed reasoning moves, preserve disagreements, and converge on accountable outcomes. We introduce Deliberative Collective Intelligence (DCI), specifying four reasoning archetypes, 14 typed epistemic acts, a shared workspace, and DCI-CF, a converge