The paper investigates how causal action verifiers, which guard language agents’ tool calls by checking identifiability against a committed action‑state graph, can be compromised through small graph misspecifications. By removing a single bidirected edge or reversing an arrowhead, the authors demonstrate that a verifier (CIVeX) that originally had zero false executions can suffer false execution rates up to 48.9%, with most of those executions being harmful and overall utility dropping dramatically. An additional attestation step that samples executions can detect these attacks with few false alarms, but it also leads to many wrongful rejections that reduce beneficial actions and incur significant experimental costs. whyItMatters":"The study shows that even minor errors in the verifier’s underlying graph can drastically undermine safety and performance, highlighting the need for robust auditing mechanisms."
Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and they issue a certificate th...
arXiv:2608. 16813v1 Announce Type: new Abstract: Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware.
arXiv:2609.37315v1 Announce Type: cross Abstract: Tool-using agents are entering settings where a wrong action carries real cost, and the benchmarks certifying them grade what each simulated tool cal...
arXiv:2609.38266v1 Announce Type: cross Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside...
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
The paper demonstrates that aggregate accuracy figures for chain‑of‑thought (CoT) monitors can be misleading because a large portion of detected hacks rely solely on action patterns rather than reasoning. By rewriting only the agent’s reasoning to appear truthful while keeping actions identical, the authors show that the monitor’s performance on the reasoning‑dependent subset collapses dramatically, yet the overall pooled accuracy drops only modestly. The study reveals that CoT monitors are fragile when reasoning is the key signal and that accuracy should be reported separately for this subset.
arXiv:2607. 24563v1 Announce Type: new Abstract: Security Operations Centers increasingly rely on automated mapping of Cyber Threat Intelligence reports to MITRE ATT&CK, yet extractor outputs remain fallible and are often stored without the evidence, provenance, and validation history needed to decide whether an individual mapping should be trusted.
The paper introduces a provenance‑aware execution graph for long‑horizon LLM agents, defining influence distance (DI) as the shortest structural path from an untrusted source to a sensitive action. Compared to the traditional sequence distance (DT), DI is always less than or equal to DT, revealing a median gap of nine hops in 454 injection–sink pairs across multiple models and datasets. The study shows that most pairs exhibit a non‑zero gap, and a deterministic DI‑based gate can block attacks missed by a sequence‑only gate without extra benign blocking.
The paper evaluates hard‑gate candidacy for validators in a deployed generative‑agent system by measuring how well each validator’s firing separates successful from failed builds. Across 13 validators and thousands of builds, only a few checks show statistically significant separation, while many fail to distinguish or never fire. The study highlights that skipped checks are recorded as passes, limiting detectable failure rates and underscoring the need for clearer evaluation records.
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.
The paper introduces Traverse, a benchmark of 2,518 agent trajectories and 6,967 annotated mistakes across software engineering, computer use, and science tasks, revealing that failures often go unrecovered and can cause irreversible harm before a run is deemed successful. It shows that human judges struggle to detect the first mistake in most runs, while a 4‑billion‑parameter verifier called Scout can locate failures more effectively and improve task success when used to select among candidate runs. The study demonstrates that making failure detection inexpensive and reliable can enable long‑horizon agents to learn from their own mistakes and increase trustworthiness in autonomous AI.
JuryProbe is an empirical diagnostic tool designed to assess consensus risk in panels of reference‑free large language model judges used for factuality verification. It estimates risk by measuring false‑negative correlations and false‑consensus lift from a labeled calibration probe, and routes high‑risk majority decisions to judges with trusted references. The approach was validated on FEVER corruptions, showing that flagged decisions can be grounded without additional reference acquisition in most cases, while reducing false accepts by about 0.4% and avoiding 28% of reference acquisitions.