{"ID":2861142,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03485","arxiv_id":"2510.03485","title":"Learning Efficient Guardrails for Compliance","abstract":"Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce PolicyGuardBench, a benchmark of 60k policy-trajectory pairs designed to evaluate compliance through both full-trajectory and novel prefix-based violation detection tasks. Using this dataset, we train PolicyGuard, a lightweight guardrail model that achieves strong detection accuracy while maintaining high inference efficiency. Notably, our model demonstrates robust generalization capabilities, preserving high performance even on unseen domains. These contributions establish a comprehensive framework for studying policy compliance, showing that accurate and generalizable guardrails are feasible at small scales.","short_abstract":"Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce PolicyGuardBench, a benchmark of 60k policy-trajectory pairs designed to evaluate complian...","url_abs":"https://arxiv.org/abs/2510.03485","url_pdf":"https://arxiv.org/pdf/2510.03485v2","authors":"[\"Xiaofei Wen\",\"Wenjie Jacky Mo\",\"Yanan Xie\",\"Peng Qi\",\"Muhao Chen\"]","published":"2025-10-03T20:03:19Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}