arXiv:2606. 22504v1 Announce Type: cross Abstract: Coding agents often receive broad tool access for an entire task, even when a resource is needed only for one subgoal.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
ClosureBound is a reference monitor that enforces authorization boundaries for agent skills by binding each grant to an exact dependency closure, effect ceiling, purpose, validity, and epochs. It resolves typed graph nodes, normalizes operations into an external‑effect IR, and admits actions only when a joint witness satisfies all bounds, ensuring metadata non‑authority, closure determinism, and other security properties. Empirical evaluation on 549 public skills shows many lack proper dependency declarations, underscoring the need for conservative closure discovery and broader runtime validation.
arXiv:2607. 10487v1 Announce Type: cross Abstract: LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result.
arXiv:2609.21284v1 Announce Type: cross Abstract: Long-running AI agents outlive initiating processes through credentials, delegated tasks, queues, callbacks, reservations, and provider-side operatio...
The paper investigates how tool‑using language‑model agents can safely commit changes to infrastructure when external state may change between read and commit. By distinguishing invalidating races from predicate‑preserving and irrelevant ones, the authors evaluate three commit‑time guard granularities—global epoch, read‑set version, and semantic commit predicate—using a deterministic simulator and three quantized model families. The study finds that only the complete predicate guard consistently eliminates unsafe commits, while freshness‑based guards block a large proportion of benign races and model‑side signals fail to replace precise semantic enforcement.
arXiv:2609. 00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior.
Autonomous agents that author building information models need more than access to a host API. They need a representation of what they intended, what a compiler decided on their behalf, what was refus...