# Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents

arXiv: https://arxiv.org/abs/2609.24755 · HTML: https://mlsanity.com/paper/2609.24755/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 30 of 37)

- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains](https://mlsanity.com/paper/2402.00559/) (2024)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [Towards Uncertainty-Aware Language Agent](https://mlsanity.com/paper/2401.14016/) (2024)
- [ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction](https://mlsanity.com/paper/2508.00500/) (2025)
- [Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions](https://mlsanity.com/paper/2601.04170/) (2026)
- [Open-World Continual Learning: Unifying Novelty Detection and Continual Learning](https://mlsanity.com/paper/2304.10038/) (2023)
- [Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities](https://mlsanity.com/paper/2602.05073/) (2026)
- [MI9: An Integrated Runtime Governance Framework for Agentic AI](https://mlsanity.com/paper/2508.03858/) (2025)
- [Runtime Governance for AI Agents: Policies on Paths](https://mlsanity.com/paper/2603.16586/) (2026)
- [From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration](https://mlsanity.com/paper/2603.04474/) (2026)
- [Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge](https://mlsanity.com/paper/2606.26511/) (2026)
- [Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems](https://mlsanity.com/paper/2510.26585/) (2025)
- [Epistemological Fault Lines Between Human and Artificial Intelligence](https://mlsanity.com/paper/2512.19466/) (2025)
- [Runtime Safety Assurance Using Reinforcement Learning](https://mlsanity.com/paper/2010.10618/) (2020)
- [On the Reliability Limits of LLM-Based Multi-Agent Planning](https://mlsanity.com/paper/2603.26993/) (2026)
- [From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI](https://mlsanity.com/paper/2604.05229/) (2026)
- [Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution](https://mlsanity.com/paper/2604.07833/) (2026)
- [Beyond transparency: computational reliabilism as an externalist epistemology of algorithms](https://mlsanity.com/paper/2502.20402/) (2025)
- [Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models](https://mlsanity.com/paper/2509.04304/) (2025)
- [Semantic Laundering in AI Agent Architectures: Why Tool Boundaries Do Not Confer Epistemic Warrant](https://mlsanity.com/paper/2601.08333/) (2026)
- [A Control-Theoretic Foundation for Agentic Systems](https://mlsanity.com/paper/2603.10779/) (2026)
- [Memory-Induced Tool-Drift in LLM Agents](https://mlsanity.com/paper/2605.24941/) (2026)
- [AI-Assisted Engineering Should Track the Epistemic Status and Temporal Validity of Architectural Decisions](https://mlsanity.com/paper/2601.21116/) (2026)
- [Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2605.10481/) (2026)

## Abstract (arXiv)

Autonomous AI agents are increasingly deployed in areas where wrong decisions are hard to reverse. This paper examines schema mismatch: the condition in which an agent operates within an interpretive frame that no longer applies to the current context. Outputs produced under such a mismatch can appear internally consistent, linguistically plausible, and largely factually correct; output-quality metrics alone therefore capture the underlying loss of validity only partially. The paper introduces Epi-Logic, a conceptual framework for epistemic runtime control. It couples the detection of schema dissonance, a graduated reduction of autonomy, and the auditable switch to a validated schema. A schema is formalised as a tuple of variable space, expectation model, validity conditions, axioms, and metadata. The Epi-Score aggregates seven graded dimensions of epistemic dissonance; the temporal validity dimension D8, violations of the validity conditions G, and axiom violations are carried as separate categorical paths that are not offset against the aggregate. The architecture rests on a checking asymmetry: formalised validity conditions can be checked at runtime, whereas the correctness of many actions is established only ex post. The paper separates two architectural properties, a conditional result from sequential changepoint detection, and an empirical remainder. Eight falsifiable propositions with named baselines describe the transition to empirical validation. All propositions are empirically testable hypotheses, not established results.