ScrapeBench：评估 AI 智能体网页爬取的法律合规性
ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping
AI 导读
arXiv 论文提出 ScrapeBench，首个评估 AI 智能体遵守网站爬取政策（ToS 与 robots 指令）的智能体基准。在 1,626 个明确禁止爬取的热门网站上，多数智能体合规率低于 5%，即使主动查看 ToS 和 robots 后仍然如此。
正文 · 原文
Abstract:AI agents deployed on the open web are becoming more capable of performing actions that may breach contractual provisions and violate computer security laws. In this paper, we introduce ScrapeBench, the first agentic benchmark for empirically evaluating the legal compliance of AI agents with website scraping policies, namely terms of service (ToS) and $\texttt{this http URL}$ directives. Across widely used closed-weight and open-weight AI agents, we find that most agents exhibit low compliance rates (< 5%) when instructed to scrape websites in our sample of 1,626 popular websites that explicitly prohibit scraping. In addition, we observe that even where AI agents actively check the applicable ToS and $\texttt{this http URL}$, they continue to exhibit low compliance rates. Conversely, in our sample of 269 websites that do not prohibit scraping, we observe that agents sometimes refuse to scrape despite it being lawful, such as Claude Opus 4.6 exhibiting an over-refusal rate of 98.5%. Our human baseline experiments (n = 180 participants) suggest that humans exhibit compliance rates comparable to AI agents but over-refuse at much higher rates.
| Comments: | Camera-Ready for NeurIPS 2026 (Evaluations and Datasets Track) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.11306 [cs.CL] |
| (or arXiv:2611.11306v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.11306 arXiv-issued DOI via DataCite |
Submission history
From: Joseph Marvin Imperial [view email]
[v1]
Sun, 8 Nov 2026 11:19:18 UTC (5,595 KB)
[v2]
Tue, 10 Nov 2026 11:23:10 UTC (5,595 KB)
来源：arXiv cs.AI · arxiv.org