思想与言语解耦：基于知识反事实推理的鲁棒多智能体辩论
Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation
AI总结：
提出知识反事实推理（KG-CFR）双阶段架构，通过私有规划缓冲与公共执行层分离，在动态资源分配环境下将扰动后论证质量从0.694提升至0.822，并减少语义循环。
摘要：
多智能体辩论框架已被证明能提升大语言模型在收敛任务上的表现，但目前优化方式过度偏向最终输出准确性而非过程稳定性。在长时间交互中，持续扰动下的反应式系统常出现逻辑退化、论点重复和角色漂移。为从结构上防止身份丢失并保持过程保真度，我们引入知识反事实推理（KG-CFR），一种双阶段架构，在私有检索增强规划缓冲区和公共执行层之间强制执行严格关注点分离。我们在不确定性下动态资源分配（DRAU）这一专用1v1v1环境中评估该系统，引入与标准辩论设置不同的多样性。在270次完全析因危机模拟轨迹（含随机环境冲击）中，KG-CFR在超过95%的扰动运行中防止了裁判检测到的关键冲击后退化（定义为质量偏移Δ ≤ -0.20），将整体论证质量从0.694提升至0.822。我们的主要贡献是证明架构解耦是在持续压力下不损失质量而增强系统鲁棒性的重要因素。此外，我们引入了用于话语发散和计划执行对齐的自定义向量度量，为操作稳定性提供了强有力且方向一致的证据。消融实验表明，适当的教义基础与前瞻规划对论证质量同等重要。根据初步度量评估，KG-CFR通过保持智能体与原始计划的一致性减少了语义循环。
英文摘要：
Multi-agent debate frameworks have been shown to improve large language model performance in convergent tasks, but they are currently optimized in a way that heavily favors final output accuracy rather than stability of the process. During long-horizon exchanges reactive systems under sustained perturbations often experience logic degradation, argument repetition, and role drift. To structurally prevent the identity loss and maintain the process fidelity, we introduce Knowledge-Grounded Counterfactual Reasoning (KG-CFR), a dual-stage architecture that enforces a strict separation of concerns between a private, retrieval-augmented planning buffer, and a public execution layer. We assess this system in Dynamic Resource Allocation under Uncertainty (DRAU), a dedicated 1v1v1 environment, introducing diversity as distinct from standard debate settings. Over 270 completely factorial crisis simulation trajectories with stochastic environmental shocks, KG-CFR prevents judge-detected critical post-shock degradation (defined as a quality shift, $Δ\le -0.20$) in more than 95% of perturbed runs, increasing the overall argument quality from 0.694 to 0.822. Our primary contribution is the demonstration of architectural decoupling being an important factor of systemic resilience enhancement under sustained pressure without quality loss. Furthermore, we introduce custom vector metrics for discourse divergence and plan-execution alignment that provide strong, directionally consistent evidence of operational stability. Our ablation experiments suggest that the proper doctrinal grounding can be an equally important factor for argument quality, as the prospective planning. KG-CFR, according to our initial metric evaluations, reduces semantic looping, by preserving the agent's consistency with the original plan.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
