Robust Agent Compensation (RAC): Teaching AI Agents to Compensate

Srinath Perera; Kaviru Hapuarachchi; Frank Leymann; Rania Khalaf

cs.AIMay 5, 2026

Robust Agent Compensation (RAC): Teaching AI Agents to Compensate

Authors: Srinath Perera, Kaviru Hapuarachchi, Frank Leymann, Rania Khalaf

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 $τ$ -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.

Explore similar work

Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection
Aug 12, 2026Chaoran Chen, Vy Nguyen, Ziji Zhang +7Retrying Multi-Turn Tool-Use Agent
Human-Guided Harm Recovery for Computer Use Agents
Apr 20, 2026Christy Li, Sky CH-Wang, Andi Peng +1Computer-Use Agents Harms
Auto: The AGI Compiler
Jul 5, 2026Jaber Jaber, Osama JaberAuto Research

Aug 12, 2026 · cs.AIJ/K move · Enter open · S save

Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection

Chaoran Chen, Vy Nguyen, Ziji Zhang, Abhinav Gullapalli+6

Amazon

Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, persistently, or silently. Robust recovery therefore requires more than repeated retries: an agent may need to retry the same path, switch to an alternative, or recognize that no viable path remains. We present BENCH2ROBUST, a framework that converts failure-free tool-use benchmarks into controlled stochastic environments with scenario-controlled solvability, where episodes explicitly require retrying, switching, or stopping after available paths are exhausted. We use BENCH2ROBUST to study two complementary interventions: structured runtime recovery context through Bayesian Tool Memory (BTM), and curriculum-controlled reinforcement learning. Across 7 models from 4 families and two multi-turn benchmark families, tool failures produce a near-universal robustness gap. On held-out Retail tasks, BTM improves robustness by up to 16.8 percentage points without retraining, while RL learns complementary recovery behavior that remains beneficial without inference-time BTM. Combining the two reaches 40.8-45.5% under injection while preserving failure-free performance. These results suggest that robust tool use benefits from combining environment-specific recovery knowledge with learned recovery behavior.

Retrying Multi-Turn Tool-Use Agent Abstention Switch Bayesian

Open paper Ask about it PDF

Abstract

Explore similar work

Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection

Human-Guided Harm Recovery for Computer Use Agents

Auto: The AGI Compiler