paper-with-me

홈 › Papers

Permission Manifests for Web Agents

2025-12-07 · Samuele Marro, Alan Chan, Xinxing Ren, Lewis Hammond, Jesse Wright, Gurjyot Wanga, Tiziano Piccardi, Nuno Campos, Tobin South, Jialin Yu, Sunando Sengupta, Eric Sommerlade, Alex Pentland, Philip Torr, Jiaxin Pei arxiv

The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conventions, such as robots$.$txt, modern agents engage with websites in sophisticated ways: navigating complex interfaces, extracting structured information, and completing end-to-end tasks. Existing governance mechanisms were not designed for these capabilities. Without a way to specify what interactions are and are not allowed, website owners increasingly rely on blanket blocking and CAPTCHAs, which undermine beneficial applications such as efficient automation, convenient use of e-commerce services, and accessibility tools. We introduce agent-permissions$.$json, a robots$.$txt-style lightweight manifest where websites specify allowed interactions, complemented by API references where available. This framework provides a low-friction coordination mechanism: website owners only need to write a simple JSON file, while agents can easily parse and automatically implement the manifest's provisions. Website owners can then focus on blocking non-compliant agents, rather than agents as a whole. By extending the spirit of robots$.$txt to the era of LLM-mediated interaction, and complementing data use initiatives such as AIPref, the manifest establishes a compliance framework that enables beneficial agent interactions while respecting site owners' preferences.

📄 PDF Abstract BibTeX arXiv:2601.02371

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

2026-05-26 · Xiaochong Jiang, Shiqi Yang, Ziwei Li, Lifei Liu 외 arxiv

Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This creates a safety gap in tool compositio…

Towards Automating Data Access Permissions in AI Agents

2025-11-22 · Yuhao Wu, Ke Yang, Franziska Roesner, Tadayoshi Kohno 외 arxiv

As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conv…

AC4A: Access Control for Agents

2026-03-21 · Reshabh K Sharma, Dan Grossman arxiv

Large Language Model (LLM) agents combine the chat interaction capabilities of LLMs with the power to interact with external tools and APIs. This enables them to perform complex tasks and act autonomously to achieve user…

Janus: a Playground for User-Involved Agentic Permission Management

2026-07-01 · Natalie Grace Brigham, Eugene Bagdasarian, Tadayoshi Kohno, Franziska Roesner arxiv

AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and what role should they play? Despite many proposed approaches, the us…

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents

2025-12-11 · Jinhao Zhu, Kevin Tseng, Gil Vernik, Xiao Huang 외 arxiv

Tool calling agents are an emerging paradigm in LLM deployment, with major platforms such as ChatGPT, Claude, and Gemini adding connectors and autonomous capabilities. However, the inherent unreliability of LLMs introduc…