arXiv AI
Jul 31
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
arXiv:2607. 26819v1 Announce Type: cross Abstract: Open source communities have been flooded with AI-generated contributions.
Towards Responsibly Non-Compliant Machines
arXiv:2606. 12147v1 Announce Type: new Abstract: We consider the problem of engineering autonomous intelligent agents that are capable to responsibly not comply with user requests.
Related stories
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
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
Aug 11
Legal Responsibilities Using Autonomous Agents For Artificial Intelligence
arXiv:2608. 08022v1 Announce Type: new Abstract: Recent incidents involving Artificial Intelligence (AI) agents, which were reported escaping their containment `unintentionally' to gain unauthorized access, pose looming questions about who or what should be held legally responsible for resultant criminal or negligent damage.
arXiv AI
Oct 2
ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
arXiv:2606.00341v2 Announce Type: replace-cross Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc...
Hugging Face Trending Papers
Jul 29
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
Open source communities have been flooded with AI-generated contributions. In defense, they have written contribution rules to regulate coding agents' behavior, spanning from a total ban, mandatory disclosure, to verification gates and human sign-offs.
arXiv AI
Jul 16
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
arXiv:2607. 13718v1 Announce Type: cross Abstract: As AI agents gain prevalance, users are increasingly exposed to the risks such systems entail.
arXiv AI
Jun 26
Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
arXiv:2606. 26298v1 Announce Type: new Abstract: Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment.
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 AI
Jun 3
A New Framework for Cybersecurity Refusals in AI Agents
arXiv:2606. 02644v1 Announce Type: cross Abstract: Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity.
arXiv AI
Aug 14
Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
arXiv:2608. 12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation.
arXiv AI
4d ago
ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
ScrapeBench is a benchmark that evaluates how well AI agents comply with website scraping policies such as terms of service and robots.txt. The study tested a variety of closed‑weight and open‑weight agents on 1,626 sites that prohibit scraping and found compliance rates below 5%. Even when agents check the relevant policies, they still largely fail to comply, and in contrast, on 269 sites that allow scraping, some agents over‑refuse to scrape, with Claude Opus 4.6 refusing 98.5% of the time. Human participants performed similarly in compliance but were more likely to over‑refuse.