AI Agents 相关度: 9/10

From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts

Sunil Prakash
arXiv: 2603.11781v1 发布: 2026-03-12 更新: 2026-03-12

AI 摘要

论文提出DCI框架,通过结构化集体推理实现LLM系统中更高效的决策制定。

主要贡献

  • 提出DCI框架,包含推理原型、知识行为和共享工作空间
  • 设计DCI-CF算法,保证决策过程终止和结果结构化
  • 实验证明DCI在复杂任务中优于非结构化辩论

方法论

通过定义推理原型、知识行为和算法,构建结构化集体推理框架,并在多领域任务上进行实验验证。

原文摘要

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.

标签

多智能体 LLM 推理 决策 结构化

arXiv 分类

cs.AI cs.CL cs.MA