# Verification of Adaptive Agentic Controllers through Finite Rule Revision

arXiv: https://arxiv.org/abs/2607.09770 · HTML: https://mlsanity.com/paper/2607.09770/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 10 of 10)

- [Formal Policy Enforcement for Real-World Agentic Systems](https://mlsanity.com/paper/2602.16708/) (2026)
- [Continual Learning for Predictive Maintenance: Overview and Challenges](https://mlsanity.com/paper/2301.12467/) (2023)
- [Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments](https://mlsanity.com/paper/2411.00186/) (2024)
- [Foundation Models for Demand Forecasting via Dual-Strategy Ensembling](https://mlsanity.com/paper/2507.22053/) (2025)
- [Agentic AI in Industry: Adoption Level and Deployment Barriers](https://mlsanity.com/paper/2605.14675/) (2026)
- [An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design](https://mlsanity.com/paper/2511.19726/) (2025)
- [Runtime Verification of Self-Adaptive Systems with Changing Requirements](https://mlsanity.com/paper/2303.16530/) (2023)
- [Complementary Fusion of Deep Network and Tree Model for ETA Prediction](https://mlsanity.com/paper/2407.01262/) (2024)
- [Dynamic Ensemble Learning for Credit Scoring: A Comparative Study](https://mlsanity.com/paper/2010.08930/) (2020)
- [Machine-Coached Policy Revision in Adaptive Agent-Based Regulatory Simulation: A Controller-Level Contestability Layer](https://mlsanity.com/paper/2606.20700/) (2026)

## Abstract (arXiv)

Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may generate plausible outputs while remaining difficult to verify under non-determinism, confidentiality constraints, limited context, and weak observability. This paper formulates a bounded verification protocol for adaptive agentic controllers represented by finite symbolic rules, explicit diagnostic predicates, explanation logs, and held-out re-evaluation. The central research question is: when an adaptive agentic controller is represented through finite rules, explicit diagnostic predicates, explanation logs, and held-out re-evaluation, which classes of controller failure can be detected, locally repaired, or rejected without relying on unrestricted human-in-the-loop judgment? The proposed framework treats the controller as a finite revisable object. Diagnostic failures are mapped to predefined rule-level edits, including rule addition, rule deletion, and priority revision. Repaired controllers are then evaluated on held-out simulation seeds or cloned initial states. Experiments in a stylized financially constrained inventory-control benchmark show three outcomes: resource-induced failures that remain non-repairable by one rule edit, partial repairs that are rejected because they violate thresholds or guardrails, and a local one-step repair of an order-volatility failure induced by removing a smoothing rule. The contribution is methodological and provides a simulation-compatible procedure for testing whether specific controller-level failures can be made observable, explainable, locally revisable, and empirically re-tested under controlled conditions.