Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Recourse, a smart-contract settlement protocol designed to address the residual harm caused by autonomous agents executing actions across organizational boundaries. By binding each action to specific parameters such as scope, recovery, and collateral, Recourse effectively separates eligibility from settleability, allowing for both objective and subjective claims to be managed through a structured arbitration process. The implementation and evaluation of Recourse demonstrate a significant reduction in uncompensated harm compared to traditional authorization-only and local-compensation methods, showcasing its potential for enhancing trust in cross-organizational interactions.
Bonded coverage through smart contracts can dramatically reduce uncompensated harm from autonomous agent actions, transforming how organizations manage liability.
Autonomous agent runtimes execute tool actions that mutate databases, repositories, and cloud services across organizational boundaries. Authorization and local compensation cover pre-action admission and in-runtime rollback, but neither settles the residual harm left after a permitted action fails. We design Recourse, a smart-contract settlement protocol for compensable agent side effects that binds each admitted action to scope, recovery, evidence, payout, and collateral. Recourse separates ex ante eligibility from ex post objective settleability: typed receipts make objective residual claims computable under an optimistic-oracle challenge pattern, while subjective or incomplete claims route to ERC-792 arbitration or exclusion. We implement the contract suite, deploy it on Base Sepolia, build adapters against Postgres, Git, and cloud-compatible local sandboxes, and evaluate the system on a deterministic harness, sandbox traces, adversarial sweeps, and property-based fuzzing. Against authorization-only and local-compensation baselines, bonded coverage cuts uncompensated harm. The on-chain tier supplies neutral custody, public challenge, non-cooperative payout, and portable history under cross-organizational trust assumptions.