arXiv AI
Aug 18
Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance
arXiv:2608. 16055v1 Announce Type: new Abstract: Existing agent benchmarks ask whether the agent finished the task.
When Agent Governance Helps
Related stories
arXiv AI
Sep 18
Governance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systems
The paper introduces Governance-as-Code (GaC), a framework that translates the EU AI Act’s technical requirements into 43 machine‑checkable acceptance criteria across six compliance modules. GaC runs within a CI/CD pipeline, producing Article‑indexed audit evidence and providing actual Rego policy code. The authors validate GaC on two enterprise deployments, showing it reproduces manual audit findings—including three penalty‑triggering violations—while reducing audit labor by about 75%.
arXiv AI
Jul 29
HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following
arXiv:2607. 25398v1 Announce Type: new Abstract: Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context, and the agent is trusted to let it govern every action that follows.
arXiv AI
Sep 4
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
arXiv:2609. 03553v1 Announce Type: new Abstract: Policy analysis requires more than predicting whether a proposal will pass: it requires identifying who will be affected, how those actors respond, and what follows.
arXiv AI
Oct 1
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
arXiv:2605.16679v3 Announce Type: replace-cross Abstract: End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density,...
arXiv AI
Sep 25
Who Holds the Pen? Let Specifications, Not Agents, Sign Off
The paper argues that large language model agents should not be the sole authority on whether they have satisfied a task. It identifies two gaps—understanding–execution and state–authority—where agents may claim completion without actually meeting the specification. The authors propose SpecHarness, a framework that separates agent proposals from authoritative state by requiring evidence from qualified providers to confirm compliance, and demonstrate its effectiveness on guideline‑following and artifact‑generation tasks.
arXiv AI
Jul 7
AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
arXiv:2607. 03656v1 Announce Type: cross Abstract: Large Language Models are increasingly used to turn natural-language requirements into code.
arXiv AI
Aug 19
Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution
The paper introduces Aegis, a runtime governance system for agentic AI that treats model outputs as action proposals and mediates them through a trusted decision layer before tool execution. Aegis evaluates proposals against active policy, resolves provenance server‑side, fails closed under uncertainty, and routes selected cases through a Senate‑style settlement process. In a sandbox evaluation across 6,300 rows, Aegis prevented all governed mock‑tool applications and risky side‑effect completions, preserving provenance and quorum evidence for all settled cases.
arXiv AI
Sep 24
Agentic Governance and Adversarial Verification for Policy-Constrained LLM Healthcare Appeal Generation
The paper introduces AGVF, a multi‑agent framework for generating medical‑necessity appeals that must adhere to payer policy and evidence constraints. AGVF treats appeal synthesis as a Constrained Markov Decision Process involving five agents—policy formalization, evidence retrieval, gap analysis, adversarial critique, and gated synthesis—and proves that refining the policy constraint graph monotonically reduces evidence deficiency. A deterministic citation‑grounding gate ensures no unsupported assertions enter the shared state, and validation on 1,000 synthetic cases shows zero citation violations and monotonic deficiency reduction.
arXiv AI
Jul 21
Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI
arXiv:2607. 17225v1 Announce Type: cross Abstract: Agentic AI systems do not just predict or recommend; they plan, maintain state, and act in external environments with varying degrees of autonomy.
arXiv AI
Oct 1
Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents
The paper introduces Runtime Assurance Contracts (RAC) as a formal policy framework for high‑risk AI agents, addressing the "assurance‑transition gap" by binding autonomy boundaries, component eligibility, evidence state, transition policy, human‑review capacity, and non‑compensatory gates. RAC allows soft metrics to influence routing while mandating retries, switches, escalations, deferrals, or stops when mandatory gates fail or are unknown, ensuring aggregate performance cannot alone authorize action. The authors define the contract, evidence record, permission rule, and five invariants, and evaluate RAC through deterministic failure‑injection studies, hand‑authored traces, and a prospective synthetic holdout, comparing it to score‑only and restricted protocol baselines.
arXiv AI
Jun 4
Parthenon Law: A Self-Evolving Legal-Agent Framework
arXiv:2606. 04602v1 Announce Type: new Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes.