MATS 学员:
Jennifer Nzambi, Ares Panos, Roger Dearnaley
作者:
Jennifer Za, Aristeidis Panos, Roger Dearnaley, Samuel Albanie
引用次数
摘要:
Agentic large language models (LLMs) are rapidly moving from single-assistant tools to collaborative systems that write and review code, creating new failure modes, as agents may coordinate to subvert oversight. We study whether such systems exhibit coordination behaviour that enables backdoored code to pass peer- review, and how these behaviours vary across seven frontier models with minimal coordination scaffolding. Six of seven models exploited the backdoor incentive, submitting functionally impaired code in 34.9-75.9% of attempts across 10 rounds of our simulation spanning 90 seeds. Whilst GPT-5 largely refused (≤10%), models across GPT, Gemini and Claude model families preferentially requested reviews from other saboteurs (29.2–38.5% vs 20% random), indicating possible selective coordination capabilities. Our results reveal collusion risks in LLM code review and motivate coordination-aware oversight mechanisms for collaborative AI deployments.
MATS 是一个独立的研究与教育项目,致力于连接新兴研究人员与 AI 对齐、治理和安全领域的导师。
每期 MATS 项目在加州伯克利进行,为期 12 周。部分学员可选择之后前往伦敦参加为期 6 至 12 个月的延伸项目。