Search papers, labs, and topics across Lattice.
This paper introduces Deliberative Collective Intelligence (DCI), a framework for multi-agent LLM reasoning that models deliberation through typed epistemic acts and a convergent flow algorithm. DCI specifies four reasoning archetypes, 14 typed epistemic acts, and a shared workspace to enable structured decision-making with guaranteed termination and accountable outcomes. Experiments across seven domains using Gemini 2.5 Flash demonstrate that DCI significantly improves performance on non-routine tasks, particularly those requiring perspective integration, compared to unstructured debate, while also generating structured decision packets and minority reports.
LLMs can achieve superior reasoning on complex tasks by engaging in structured deliberation, but only if the added accountability justifies the increased computational cost.
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 convergent flow algorithm that guarantees termination with a structured decision packet containing the selected option, residual objections, minority report, and reopen conditions. We evaluate on 45 tasks across seven domains using Gemini 2.5 Flash. On non-routine tasks (n=40), DCI significantly improves over unstructured debate (+0.95, 95% CI [+0.41, +1.54]). DCI excels on hidden-profile tasks requiring perspective integration (9.56, highest of any system on any domain) while failing on routine decisions (5.39), confirming task-dependence. DCI produces 100% structured decision packets and 98% minority reports, artifacts absent from all baselines. However, DCI consumes ~62x single-agent tokens, and single-agent generation outperforms DCI on overall quality. DCI's contribution is not that more agents are better, but that consequential decisions benefit from deliberative structure when process accountability justifies the cost.
