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.

翻译：多智能体辩论框架已被证明能够提升大语言模型在收敛性任务上的表现，但其当前优化方式过度偏向于最终输出精确度，而忽视了过程稳定性。在长时间交互过程中，持续受到扰动影响的反应式系统常出现逻辑退化、论点重复和角色偏移等问题。为从结构上防止身份丢失并维持过程保真度，我们提出基于知识注入的反事实推理方法——一种双阶段架构，其通过严格分离私有检索增强规划缓冲层与公开执行层来实现关注点隔离。我们在不确定性环境下动态资源分配这一专用1v1v1环境中评估该系统，引入与传统辩论设置不同的多样性指标。在包含随机环境冲击的270个全因子危机仿真轨迹中，该方法能在超过95%的受扰动运行中阻止评估者检测到的关键冲击后质量退化（定义为质量偏移量Δ≤-0.20），将整体论证质量从0.694提升至0.822。我们的核心贡献在于证明架构解耦是在持续压力下增强系统鲁棒性的重要因素，且不会导致质量损失。此外，我们引入针对话语发散度与规划执行对齐度的自定义向量指标，为操作稳定性提供强有力且方向一致的证据。消融实验表明，适当的理论依据锚定对论证质量的影响与前瞻性规划同等重要。根据初步指标评估，该方法通过保持智能体与原始规划的一致性，有效减少了语义循环。