Permission Manifests for Web Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Marro, Samuele, Chan, Alan, Ren, Xinxing, Hammond, Lewis, Wright, Jesse, Wanga, Gurjyot, Piccardi, Tiziano, Campos, Nuno, South, Tobin, Yu, Jialin, Sengupta, Sunando, Sommerlade, Eric, Pentland, Alex, Torr, Philip, Pei, Jiaxin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909988401709056
author Marro, Samuele
Chan, Alan
Ren, Xinxing
Hammond, Lewis
Wright, Jesse
Wanga, Gurjyot
Piccardi, Tiziano
Campos, Nuno
South, Tobin
Yu, Jialin
Sengupta, Sunando
Sommerlade, Eric
Pentland, Alex
Torr, Philip
Pei, Jiaxin
author_facet Marro, Samuele
Chan, Alan
Ren, Xinxing
Hammond, Lewis
Wright, Jesse
Wanga, Gurjyot
Piccardi, Tiziano
Campos, Nuno
South, Tobin
Yu, Jialin
Sengupta, Sunando
Sommerlade, Eric
Pentland, Alex
Torr, Philip
Pei, Jiaxin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Permission Manifests for Web Agents
Marro, Samuele
Chan, Alan
Ren, Xinxing
Hammond, Lewis
Wright, Jesse
Wanga, Gurjyot
Piccardi, Tiziano
Campos, Nuno
South, Tobin
Yu, Jialin
Sengupta, Sunando
Sommerlade, Eric
Pentland, Alex
Torr, Philip
Pei, Jiaxin
Computers and Society
Artificial Intelligence
Multiagent Systems
Networking and Internet Architecture
I.2.7; I.2.11; H.3.5
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.
title Permission Manifests for Web Agents
topic Computers and Society
Artificial Intelligence
Multiagent Systems
Networking and Internet Architecture
I.2.7; I.2.11; H.3.5
url https://arxiv.org/abs/2601.02371