按年被提到
20262026 · 2 次2026
AI 安全、伦理与社会影响›智能体安全与滥用·arXiv:2603.00991 · cs.AI

Tracking Capabilities for Safer Agents

Martin Odersky, Yaoyu Zhao, Yichen Xu, Oliver Bračevac, Cao Nguyen Pham · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-05-20 · 最近 2026-09-20发表于 ACM Conference on AI and Agentic Systems (CAIS)
2不同的人
2活跃月份
2讨论串
2被引(OpenAlex)
arXiv 摘要(候选层不写导读)

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these challenges, we propose to put the agent in a programming-language-based "safety harness": instead of calling tools directly, agents express their intentions as code in a capability-safe language: Scala 3 with capture checking. Capabilities are program variables that regulate access to effects and resources of interest. Scala's type system tracks capabilities statically, providing fine-grained control over what an agent can do. In particular, it enables local purity, the ability to enforce that sub-computations are side-effect-free, preventing information leakage when agents process classified data. We demonstrate that extensible agent safety harnesses can be built by leveraging a strong type system with tracked capabilities. Our experiments show that agents can generate capability-safe code with no significant loss in task performance, while the type system reliably prevents unsafe behaviors such as information leakage and malicious side effects.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次