mlsanityData to 7 Oct 2026

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

arXiv 2605.03409 ↗First posted 5 May 2026cs.AIcited by 3

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 11 of its 45 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

11 of 45 references.

References · 11

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  3. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  4. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
  5. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  6. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 359
  7. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  8. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  9. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 58
  10. 2025REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Taskscited by 16
  11. 2025Hell or High Water: Evaluating Agentic Recovery from External Failurescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agentscited by 8
  2. 2026When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundarycited by 0
  3. 2026Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
  2. 2026Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay
  3. 2026RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM Agents
  4. 2026Adaptive Robust Estimator for Multi-Agent Reinforcement Learning
  5. 2025Autono: A ReAct-Based Highly Robust Autonomous Agent Framework
  6. 2026AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
  7. 2026Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL
  8. 2026Belayer: Efficient Fault Tolerance for LLM Agentic RL Training