提出预算约束的审计框架，高效检测大模型多智能体系统中的错误传播。
BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placement
- 将多智能体执行建模为动态依赖图，按预算优化审计点布局。
- 在多种任务中减少17.2%~40.6%的总令牌消耗，性能接近无污染基准。
- 适合需要高可靠性与低计算成本的复杂多智能体应用。
基于大语言模型的多智能体系统（LLM-MAS）通过专业化协作解决复杂任务，但智能体间的依赖关系可能将幻觉或恶意输出传播至系统级失败。审计智能体可缓解此类风险，但现有策略面临效率困境：仅在末端审计需回滚范围大，影响检测效果；每轮全量审计虽提升定位精度，却带来高昂的令牌开销。为此，我们提出BRA-Audit，一种预算感知的运行时审计框架。该框架将多智能体系统执行建模为动态依赖图，将审计调度转化为在固定审计调用预算下最小化累积未检查暴露的审计点放置问题。其贪婪调度器优先选择具有高影响力且长期未审计的区域，可信审计点支持局部恢复。在结构化协调、复杂推理和开放式任务场景中，BRA-Audit使系统性能恢复至接近干净环境水平，优于轻量级保护方法，且端到端令牌消耗降低17.2%–40.6%。
原文摘要 · Abstract (English)
LLM-based multi-agent systems (LLM-MAS) solve complex tasks through specialized collaboration, but inter-agent dependencies can propagate hallucinated or malicious outputs into system-level failures. Auditor agents mitigate these risks, yet existing strategies face an efficiency dilemma: end-only auditing reviews long trajectories and final outputs, potentially weakening audit effectiveness and enlarging rollback scope, while auditing every agent each round improves detection and localization at high token cost. How can guard performance be preserved while minimizing token cost? To address this problem, we propose BRA-Audit, a budget-aware runtime auditing framework that models MAS execution as a dynamic dependency graph and formulates audit scheduling as audit-point placement under a fixed audit-call budget to minimize cumulative unchecked exposure. Its greedy scheduler prioritizes influential and long-unaudited regions, while trusted audit points enable localized recovery. Across structured coordination, complex reasoning, and open-ended tasks, BRA-Audit restores performance close to the clean setting, remains competitive with heavy guard methods and reduces end-to-end token consumption by \(17.2\%\)--\(40.6\%\).
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。