Robust Agent Compensation (RAC): Teaching AI Agents to Compensate
Srinath Perera (WSO2, Santa Clara, CA, USA), Kaviru Hapuarachchi (WSO2, Santa Clara, CA, USA), Frank Leymann (University of Stuttgart, Stuttgart, Germany), Rania Khalaf (WSO2, Santa Clara, CA, USA)
Architectural Patterns & Composition
Abstract
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 $\tau$²-bench and REALM-Bench, and show that when solving complex problems, RAC is 10X or more better in both latency and token economy compared to state-of-the-art LLM-based recovery approaches.
