让企业AI多智能体协作实时合规，零违规且风险可控。
Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
- 将协作决策建模为带约束的优化问题，运行时动态修正动作。
- 0违规，风险均值比0.71，92%-97%效率保留，2.4次内收敛。
- 适合需合规审计的企业级系统，可无缝接入OPA等生产引擎。
企业AI系统在关键流程中部署多个智能体，必须满足严格的政策约束、风险上限和全面可审计性（如SOX、HIPAA、GDPR）。现有协调方法——合作式多智能体强化学习、共识协议和集中式规划器——虽优化期望奖励，但隐式处理约束。本文提出CAMCO（约束感知多智能体认知编排）：一种运行时协调层，将多智能体决策建模为约束优化问题。CAMCO集成三项机制：(i) 约束投影引擎，通过凸投影强制政策可行动作；(ii) 自适应风险加权拉格朗日效用塑造；(iii) 可证明收敛的迭代协商协议。不同于训练期约束强化学习，CAMCO作为部署期中间件，兼容任意智能体架构，其策略谓词可直接集成至生产引擎（如OPA）。在三个企业场景中的评估显示：零政策违规，风险暴露低于阈值（均值比0.71），效用保留率达92%-97%，平均收敛于2.4次迭代。
原文摘要 · Abstract (English)
Enterprise AI systems increasingly deploy multiple intelligent agents across mission-critical workflows that must satisfy hard policy constraints, bounded risk exposure, and comprehensive auditability (SOX, HIPAA, GDPR). Existing coordination methods - cooperative MARL, consensus protocols, and centralized planners - optimize expected reward while treating constraints implicitly. This paper introduces CAMCO (Constraint-Aware Multi-Agent Cognitive Orchestration), a runtime coordination layer that models multi-agent decision-making as a constrained optimization problem. CAMCO integrates three mechanisms: (i) a constraint projection engine enforcing policy-feasible actions via convex projection, (ii) adaptive risk-weighted Lagrangian utility shaping, and (iii) an iterative negotiation protocol with provably bounded convergence. Unlike training-time constrained RL, CAMCO operates as deployment-time middleware compatible with any agent architecture, with policy predicates designed for direct integration with production engines such as OPA. Evaluation across three enterprise scenarios - including comparison against a constrained Lagrangian MARL baseline - demonstrates zero policy violations, risk exposure below threshold (mean ratio 0.71), 92-97% utility retention, and mean convergence in 2.4 iterations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。