arXiv cs.AI· Zuyao Xu, Xiang Li·· 12 小时前AI 评分38
Proof-of-Agentness：如何验证 Web 上的 AI 智能体
Proof-of-Agentness: Towards Verifying Agents on the Web
AI 导读
论文提出 Proof-of-Agentness（PoA）机制，用于区分 LLM 驱动的智能体与其他自动化客户端（如简单机器人和脚本），以应对 Web 服务将智能体视为合法用户后出现的大规模垃圾提交问题。
正文
Abstract:CAPTCHAs and bot detection have helped protect Web services from automated abuse for decades by distinguishing humans from bots. However, the emergence of LLM-powered agents introduces a new setting: Web services increasingly accommodate agents as legitimate users. Without a way to distinguish agents from other automated clients such as simple bots and scripts, these services risk large-scale automated junk submissions that waste service resources and consume users' attention or tokens. In this paper, we investigate a novel question for today's Web: "How can a Web service obtain evidence that a client is an agent?" We introduce the concept of "Proof-of-Agentness" (PoA), a mechanism for distinguishing agents from other automated clients, motivated by the parallel between human attention and an agent's inference resources. We outline two approaches: active verification through challenge-response and passive analysis of service-visible signals. Eight language models achieve an overall accuracy of 96.5% on our challenges, with an average overhead of 1,647 tokens. For passive analysis, we conduct an IRB-approved user study comparing the Web interactions of twelve human participants and representative Bot and Agent implementations, achieving an average classification accuracy of 95.8% across four classifiers, motivating further study.
| Comments: | 12 pages, 7 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35288 [cs.AI] |
| (or arXiv:2610.35288v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35288 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zuyao Xu [view email]
[v1]
Mon, 26 Oct 2026 11:59:42 UTC (929 KB)
来源：arXiv cs.AI · arxiv.org