arXiv Machine Learning
Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 16
BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and...
arXiv AI
5d ago
Runtime Control for AI Agents: Closing the Evaluation--Execution Gap in Operational Workflows
The paper introduces a runtime assurance layer for language‑model agents operating in operational workflows, addressing the evaluation–execution gap where approvals may become invalid after changes in facts, evidence, policy, or authority. The proposed state‑bound configuration separates probabilistic measurement from deterministic adjudication, binds execution allowances to the basis of an approval, invalidates them upon logged changes, and rechecks admissibility at dispatch. In a scripted 42‑case replay, the approach identified 15 later‑invalidated approvals that a non‑re‑evaluating comparator missed, holding 14 affected actions before dispatch and compensating one landed effect.
arXiv AI
Aug 28
Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents
The paper demonstrates that safety mechanisms for autonomous large language model agents fail to compose across iterative loops, as trajectory‑scoped monitors cannot detect attacks whose evidence is spread over multiple iterations. It introduces LoopHarness, a system that maintains a persistent, non‑decaying safety state across loops, bounding unauthorized actions with a constant that does not grow with the number of iterations. The authors provide a comprehensive evaluation protocol, including attacks that require cross‑iteration evidence, module ablations, and adaptive white‑box red‑team testing.
arXiv Statistics ML
4d ago
Adaptive auditing of AI systems with anytime-valid guarantees
The paper introduces a hypothesis testing framework for adaptive auditing of AI systems, addressing the challenge of limited, opportunistically collected data. It defines two competing null hypotheses—one from the model’s perspective and one from the auditor’s—and uses Safe Anytime-Valid Inference (SAVI) to perform betting-based tests that yield simultaneous e-processes. The authors prove that, with a powerful auditor, the two hypotheses become asymptotically inverse, allowing a global robustness certification, and demonstrate empirically that their methods control Type‑I error and can reach conclusions with as few as 20 observations.
Hugging Face Trending Papers
Sep 14
BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings,...
arXiv AI
Sep 10
Generator-Independent Runtime Assurance under Partial Observation
arXiv:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box \emph{generators}---are increasingly deployed behind runtim...