Five Primitives for Governing Autonomous AI Agents at Runtime

• URL: http://arxiv.org/abs/2608.26696v1
• Date: Thu, 27 Aug 2026 06:53:11 GMT
• Title: Five Primitives for Governing Autonomous AI Agents at Runtime
• Abstract summary: We argue that governing autonomous AI agents is a problem, not a model-alignment problem.<n>We derive five primitives from the questions that must be answered before an action takes effect.<n>We describe an implementation in which an agent's action is mediated against policy before it takes effect.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Enterprise deployments of autonomous AI agents inherit a control model built for human users and long-lived services, and the fit fails in three specific ways: agent principals are ephemeral, appearing and vanishing faster than provisioning; their actions are selected by a model rather than programmed, so the set of things they may attempt is not known in advance; and the population is discovered rather than provisioned, because anyone who can call an API can create one. We argue that governing such agents is a runtime problem -- not a model-alignment problem and not a build-time problem -- and we derive five primitives from the questions that must be answered before an action takes effect and after it has: discovery, identity, governance, attestation, and supply chain. For each we state what fails if it is absent and why the others cannot structurally supply it. We describe an implementation in which an agent's action is mediated against policy before it takes effect, authorised against a per-tenant action vocabulary, and recorded in a hash-linked signed ledger a third party can verify with the vendor out of the loop. We report what the architecture costs: the enforcement point sits on the request's critical path, identity requires a sidecar per workload, and fail-closed mediation converts availability incidents into denial. We are explicit about implementation status: four primitives are built and running in private pilots, and the fifth is built as separate tooling and not yet integrated into the request path. We keep it in the set deliberately: a five-part decomposition that exactly matches what its authors happened to build is not a taxonomy but a description of a codebase.

Related papers

• Where Accountability Lives: Mapping Human Responsibility to Workflow Artifacts in Agentic Software Development [0.0]
  Coding agents author, open pull requests, and push code in production repositories.<n>We read both against the workflow events that leave artifacts, across four agentic coding tools and eighteen governing policy documents from seven providers.<n>One provider bars the developer who assigned a task from approving the resulting pull request; another documents an agent that approves pull requests below a configured risk threshold and can dismiss reviews.<n>We replace the usual three-way distinction between enforced, advisory and absent verification with a grid separating whether a mechanism compels the check from who performs it.
  arXiv  Detail & Related papers  (2026-08-16T11:11:04Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents [56.187590188698955]
  Large Language Models have enabled increasingly capable autonomous agents, yet personalization remains critical for making such agents practically useful.<n>Recent benchmarks have begun evaluating personalization in agents, but they largely rely on static preference snapshots, fixed interaction logs, or question answering over predefined user profiles.<n>We introduce IBA-Bench, a benchmark for implicit behavioral alignment constructed from longitudinal interaction histories.<n>We propose IBA-Agent, an agent framework that reconciles conflicting priorities through broad retrieval and trajectory-level alignment.
  arXiv  Detail & Related papers  (2026-08-03T12:52:04Z)
• Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation [0.0]
  We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language model agent.<n>The unit of investigation is the session rather than the event, and the session key is obscured by the identity layering federated credentials introduce.<n>Across ten controlled AWS S3 scenarios, nine were reconstructed completely, no report contained an assertion untraceable to an observed artifact, and latency was four to five minutes.
  arXiv  Detail & Related papers  (2026-07-27T05:05:57Z)
• Dynamic Capability Scoping for Enterprise AI Agents: A Synthetic Dataset and Three-Source Permission Architecture [0.0]
  We argue that capability scoping must follow a dynamic least-privilege principle and be treated as a prevention mechanism before a detection.<n>A credential that does not exist in an agent's context cannot be misused regardless of the agent's reasoning.<n>We contribute a synthetic dataset of 600 enterprise task prompts grounded in a multi-department company policy.
  arXiv  Detail & Related papers  (2026-07-24T16:08:03Z)
• Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? [54.701199583505144]
  Cross-application access creates a privacy risk that has been largely overlooked.<n>We introduce AgentCIBench, an evaluation harness that turns this risk into executable, deterministically scored scenarios.<n>We evaluate 15 frontier agents and find a surprisingly high failure rate.
  arXiv  Detail & Related papers  (2026-06-22T11:36:58Z)
• A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents [0.0]
  We present a reference architecture for the governance of production AI agents.<n>We define a taxonomy of six interruption primitives that generalize allow and deny, state and argue for four correctness invariants.<n>We demonstrate the foreclosure of seven production-agent threats across five concrete adjudications.
  arXiv  Detail & Related papers  (2026-06-10T16:54:47Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure [0.0]
  We call this problem authorization propagation.<n>It is not reducible to prompt injection and is not fully addressed by classical access-control models such as RBAC, ABAC, or ReBAC.<n>The paper formalizes authorization propagation as a workflow-level property, identifies three sub-problems, and derives seven structural requirements for authorization architectures in multi-agent AI systems.
  arXiv  Detail & Related papers  (2026-05-06T20:56:17Z)
• Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning [58.432996881401415]
  Recent work augments large language models (LLMs) with external tools to enable agentic reasoning.<n>We propose Sponge Tool Attack (STA), which disrupts agentic reasoning solely by rewriting the input prompt.<n>STA generates benign-looking prompt rewrites from the original one with high semantic fidelity.
  arXiv  Detail & Related papers  (2026-01-24T19:36:51Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.