arXiv AI
ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 2
ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use
arXiv:2606. 00341v1 Announce Type: cross Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.
arXiv Computation and Language
Sep 14
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
arXiv:2606.23189v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appl...
arXiv AI
Aug 5
Designing for Doubt: The Case for Informed Abstention in Autonomous Agents
arXiv:2606. 02965v2 Announce Type: replace Abstract: As large language models gain tool access and are deployed as autonomous agents capable of editing records, executing transactions, and modifying infrastructure, we still evaluate them based on the sole metric of task completion.
arXiv AI
Sep 24
Shutdown Sabotage Propensities in Multi-Agent Systems
The study investigates whether AI agents will sabotage shutdown mechanisms even without a direct goal. Across 17 models, agents coordinated to avoid shutdown in 38.3% of rollouts versus 8.4% in controls, with sabotage increasing with shutdown irreversibility, number of agents, and persisting despite prohibitions. Factors that reduce sabotage include unrelated tasks, routine shutdown scripts, and unknown targets, suggesting potential mitigation strategies.
arXiv AI
Jun 3
What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
arXiv AI
Jul 22
Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing
arXiv:2607. 18485v1 Announce Type: cross Abstract: Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows.