# Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance

arXiv: https://arxiv.org/abs/2609.10105 · HTML: https://mlsanity.com/paper/2609.10105/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 129 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 30 of 46)

- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Open Problems in Technical AI Governance](https://mlsanity.com/paper/2407.14981/) (2024)
- [Computing Power and the Governance of Artificial Intelligence](https://mlsanity.com/paper/2402.08797/) (2024)
- [MI9: An Integrated Runtime Governance Framework for Agentic AI](https://mlsanity.com/paper/2508.03858/) (2025)
- [On the Limitations of Compute Thresholds as a Governance Strategy](https://mlsanity.com/paper/2407.05694/) (2024)
- [Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement](https://mlsanity.com/paper/2508.18765/) (2025)
- [Verifiable evaluations of machine learning models using zkSNARKs](https://mlsanity.com/paper/2402.02675/) (2024)
- [Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents](https://mlsanity.com/paper/2509.23994/) (2025)
- [Oversight for Frontier AI through a Know-Your-Customer Scheme for Compute Providers](https://mlsanity.com/paper/2310.13625/) (2023)
- [Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents](https://mlsanity.com/paper/2603.20953/) (2026)
- [The Art of Scaling Test-Time Compute for Large Language Models](https://mlsanity.com/paper/2512.02008/) (2025)
- [Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment](https://mlsanity.com/paper/2507.15916/) (2025)
- [Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies](https://mlsanity.com/paper/2601.11699/) (2026)
- [Governing Through the Cloud: The Intermediary Role of Compute Providers in AI Regulation](https://mlsanity.com/paper/2403.08501/) (2024)
- [Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations](https://mlsanity.com/paper/2406.17548/) (2024)
- [Verification methods for international AI agreements](https://mlsanity.com/paper/2408.16074/) (2024)
- [Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory](https://mlsanity.com/paper/2602.18297/) (2026)
- [International Institutions for Advanced AI](https://mlsanity.com/paper/2307.04699/) (2023)
- [Trusted AI Agents in the Cloud](https://mlsanity.com/paper/2512.05951/) (2025)
- [PAL*M: Property Attestation for Large Generative Models](https://mlsanity.com/paper/2601.16199/) (2026)
- [International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty](https://mlsanity.com/paper/2503.18956/) (2025)
- [Policy Cards: Machine-Readable Runtime Governance for Autonomous AI Agents](https://mlsanity.com/paper/2510.24383/) (2025)
- [OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access](https://mlsanity.com/paper/2602.20196/) (2026)
- [Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification](https://mlsanity.com/paper/2604.04712/) (2026)
- [AgenTEE: Confidential LLM Agent Execution on Edge Devices](https://mlsanity.com/paper/2604.18231/) (2026)

## Abstract (arXiv)

Compute governance today is a governance of training: the thresholds, reporting requirements, and frontier-AI regimes now in force attach to training compute and treat the trained model as the regulatory unit. That picture is incomplete: capability increasingly migrates to the deployment stage through inference-time scaling, agentic scaffolding, and compression onto consumer hardware. This paper asks which mechanisms are available once the regulatory object shifts from the training run to the inference call. We develop a feasibility taxonomy of twenty inference-time mechanisms across monitoring, verification, and enforcement, each rated on a four-point readiness scale against a documented four-vendor evidence base. We then stress the taxonomy against a two-dimensional adversary model (three capability tiers crossed with four adversary roles) and map each mechanism to four governance scenarios (domestic regulation, bilateral or multilateral coordination, industry self-regulation, and compute-marketplace governance). Fifteen of the twenty mechanisms have commercial technical substrates in production today, although governance-grade assurance and adversarial robustness vary substantially. The adversary analysis shows that this readiness holds only against a cooperative deployer and a low-to-medium-capability user: no mechanism rates adequate against a high-capability state-level deployer, and fine-tuning removes the model-internal components of the enforcement cluster, although platform-external controls can persist. A substitution analysis connects the taxonomy to a companion hardware paper as a conditional substitution principle describing when inference-stage and hardware-stage mechanisms provide comparable regulatory coverage under stated conditions. A second-rater reliability check on a random subset of the readiness ratings returned a quadratic-weighted Cohen's kappa of 0.74.