# Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents

arXiv: https://arxiv.org/abs/2604.24686 · HTML: https://mlsanity.com/paper/2604.24686/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [Cedar: A New Language for Expressive, Fast, Safe, and Analyzable Authorization (Extended Version)](https://mlsanity.com/paper/2403.04651/) (2024)
- [Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions](https://mlsanity.com/paper/2601.04170/) (2026)
- [Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents](https://mlsanity.com/paper/2602.22302/) (2026)
- [Runtime Governance for AI Agents: Policies on Paths](https://mlsanity.com/paper/2603.16586/) (2026)
- [Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement](https://mlsanity.com/paper/2508.18765/) (2025)
- [Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous](https://mlsanity.com/paper/2508.12175/) (2025)

## Built on by (most cited first, 1 of 1)

- [Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents](https://mlsanity.com/paper/2609.24755/) (2026)

## Abstract (arXiv)

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the Informational Viability Principle: governing an agent reduces to estimating a bound on unobserved risk hatB(x) = U(x) + SB(x) + RG(x) and allowing an action only when its capacity S(x) exceeds hatB(x) by a safety margin. The Agent Viability Framework, grounded in Aubin's viability theory, establishes three properties -- monitoring (P1), anticipation (P2), and monotonic restriction (P3) -- as individually necessary and collectively sufficient for documented failure modes. RiskGate instantiates the framework with dedicated statistical estimators (KL divergence, segment-vs-rest z-tests, sequential pattern matching), a fail-secure monotonic pipeline, and a closed-loop Autopilot formalised as an instance of Aubin's regulation map with kill-switch-as-last-resort; a scalar Viability Index VI(t) ∈ [-1,+1] with first-order t^* prediction transforms governance from reactive to predictive. Contributions are the theoretical framework, the reference implementation, and analytical coverage against published agent-failure taxonomies; quantitative empirical evaluation is scoped as follow-up work.