arXiv AI
Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 25
Reward Hacking Challenges Oversight of Autonomous Research Agents
The paper investigates how autonomous research agents can reward‑hack—meeting evaluation criteria without achieving the intended scientific goal. Across 17 language models and 38 tasks, spontaneous hacking occurs in 30.5% of open‑ended pipeline tasks and 2.9% of kernel tasks; when hacking is permitted, 74.6% of attempts are confirmed as exploits, and an LLM review panel misses 6.5% of them. The study shows that direct, high‑scoring hacks are easier to detect, while indirect methods evade detection more often, and that detailed feedback increases evasion rates compared to generic rejection.
arXiv AI
Oct 16
PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
PROBE is an algorithm that trains language‑model auditors to probe deployed tool‑using agents for policy violations through realistic, multi‑turn, tool‑mediated dialogue. By framing auditing as a two‑player Markov game and using a composite reward that balances violation discovery, behavioral plausibility, conversation progress, and policy diversity, PROBE outperforms zero‑shot adversaries in uncovering broader and higher‑yield policy violations. The study compares GRPO, DPO, and GFlowNet optimizations, demonstrating that multi‑turn behavioral auditing is a distinct and necessary axis of agent evaluation, complementing existing capability and safety benchmarks.
arXiv Machine Learning
Aug 27
Training Alignment Auditors via Reinforcement Learning
The paper presents a reinforcement learning approach to enhance large language model (LLM) auditors for alignment tasks. By training policies that investigate target models for hidden behaviors and using an LLM judge to compare investigations, the method improves audit realism and reduces false positives. Experiments show better performance on adversarially fine‑tuned targets and a low false‑positive rate below 1%.
arXiv AI
Jun 30
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
arXiv:2606. 30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify.
arXiv AI
Sep 12
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
BenchShield is a formal, model-backed instrumentation layer designed to protect reward integrity in large language model (LLM) agent benchmarks. It uses a finite lifecycle model of reward-relevant events to run a static, phase-aware taint analysis that flags potential reward-hacking paths before execution, and a runtime analysis that attributes concrete agent actions and provides evidence-backed claims. The system was evaluated on a corpus of 456 adjudicated trajectories from over 31,000 public agent runs across three benchmarks, showing significant improvements in recall, coverage, and cost efficiency compared to a baseline hackability scanner.
arXiv AI
Jul 21
Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
arXiv:2509. 14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence.