ESCROW: Guarded and Dual-Objective Continual Maintenance for Agents in Policy-Governed Enterprise Workflows

arXiv:2608.01772v2 Announce Type: replace Abstract: LLM agents increasingly run policy-bound enterprise workflows, where they must apply rules consistently and stay auditable. Deploying such an agent is the start of its long-term maintenance cycle: it must adapt to a stream of operational signals, yet reliably turning these sparse, unlabeled signals into reusable skill revisions is hard, and a careless update can trade one task category's accuracy for the overall gain, revive a resolved failure, or land at an undeployable cost. We present ESCROW, a post-deployment maintenance framework that updates an agent's external, reviewable skills under a Strict Update Boundary: the LLM proposes candidate revisions, but only an empirically evaluated version is deployed. It combines distributed diagnosis with consensus, a per-category non-regression guard, cross-cycle anti-regression, and accuracy--cost Pareto search, emitting a versioned, auditable diff per change. In real production on our internal financial document-auditing system, it attains the strongest evaluated accuracy--cost trade-off among baselines, with a transfer probe on public au-bench.

Related

• A Unified Policy Architecture (UPA): The Governance Kernel for Enterprise AI Operating Systems
• Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
• ActGov: Governing LLM Agent Actions via Policy-Constrained Validation
• When Validation Stops Learning: Auditing Update Admission for Continual Embodied Agents
• Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming

Source: arXiv cs.AI | 2026-10-02