Newest papers

AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards

Chao Shang, Wanyu Du, Yi Zhang, Sandesh Swamy · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28989 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

定制代理部署定义了工具、资源和执行条件的政策。在任务代理的提示中提供这些政策并不能可靠地防止违规行为。 培训警卫需要符合或违反这些政策的工具调用示例。 我们引入了 AgentPolicyForge,该框架使用可执行环境来构建政策基准并反复训练政策警卫。 通过这个框架,我们构建了PolicyGym,一个跨越十个政策任务家族的数据集,使用698个培训数据生成场景和254个单独的被人审查的测试套件的展开场景。 工具调用被执行,他们的结果被记录下来,以帮助确定它们是否符合政策。 每个违规案例都使用一个允许的工具,需要对论点、资源和固定任务组合进行检查,而不是单独的工具

Machine translation (Meta M2M100); the English original follows.

Abstract

Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies in the task agent's prompt does not reliably prevent violations. Training a guard requires examples of tool calls that comply with or violate those policies. We introduce AgentPolicyForge, a framework that uses executable environments to construct policy benchmarks and iteratively train policy guards. With this framework, we construct PolicyGym, a dataset across ten policy families using 698 scenarios for training data generation and 254 separate held-out scenarios for human-reviewed test sets. Tool calls are executed and their outcomes recorded to help determine whether they comply with the policy. Every violating case uses a permitted tool, requiring checks of arguments, resources, and context rather than tool identity alone. The case construction process supports iterative guard training: an attacker generates requests using retrieved strategies, and the guard is fine-tuned on balanced, environment-verified examples. Training improves policy enforcement even with a fixed archive. Updating the archive further reduces in-domain attack success compared with keeping it fixed. We compare policy-aware task agent self-regulation with a trained policy guard. On PolicyGym, the final guard-based configuration achieves a 40-44% relative reduction in attack success rate and fewer benign rejections than policy prompting alone.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Executable, Guard (computer science), Computer science, Construct (python library), Enforcement, Task (project management)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange