让AI代理自动纠错，提升执行可靠性。
Robust Agent Compensation (RAC): Teaching AI Agents to Compensate
- 通过日志回溯实现架构级容错，无需改代码即可接入
- 在复杂任务中比现有方法快1.5至8倍，节省大量计算资源
- 适合需要高可靠性的智能体系统，如自动化流程与安全关键应用
我们提出鲁棒代理补偿（RAC），一种基于日志的恢复范式，通过架构扩展为多数代理框架提供安全冗余，支持可靠执行并避免意外副作用。用户可无需修改现有代理代码（如LangGraph）启用RAC。该方法可通过现有框架的扩展点实现。我们在LangChain基础上实现，并通过τ-bench和REALM-Bench验证其可行性。结果表明，在解决复杂问题时，RAC在延迟和令牌经济性上相比最先进的基于大模型的恢复方法提升1.5至8倍以上。
原文摘要 · Abstract (English)
We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that can be applied to most Agent frameworks to support reliable executions (avoiding unintended side effects). Users can choose to enable RAC without changing their current agent code (e.g., LangGraph agents). The proposed approach can be implemented in most existing agent frameworks via their existing extension points. We present an implementation based on LangChain, demonstrate its viability through the $τ$-bench and REALM-Bench, and show that when solving complex problems, RAC is 1.5-8X or more better in both latency and token economy compared to state-of-the-art LLM-based recovery approaches.
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。