# AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI

DevFeed: [AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI](<https://devfeed.tech/articles/ai-voyager-a-public-interest-system-for-human-ai-civic-reasoning-to-contest-and-shape-the-rules-that-govern-ai-135081.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17564>)

Author: Snehalkumar \`Neil' S. Gaikwad, Dhruv Dixit, Bryen Alvarez, Pratik Patekar, Anika Sharma, Akshara Kolipaka, Paritosh Pandey

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistance](<https://devfeed.tech/tags/ai-assistance.md>), [ai-in-hiring](<https://devfeed.tech/tags/ai-in-hiring.md>), [ai-strategy](<https://devfeed.tech/tags/ai-strategy.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [changes](<https://devfeed.tech/tags/changes.md>), [city](<https://devfeed.tech/tags/city.md>), [contest](<https://devfeed.tech/tags/contest.md>), [country](<https://devfeed.tech/tags/country.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [design](<https://devfeed.tech/tags/design.md>), [public](<https://devfeed.tech/tags/public.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [rules](<https://devfeed.tech/tags/rules.md>), [shape](<https://devfeed.tech/tags/shape.md>), [system](<https://devfeed.tech/tags/system.md>), [voyager](<https://devfeed.tech/tags/voyager.md>)

## AI overview

AI-Voyager is a public-interest system for helping people understand and contest government rules about AI and propose revisions grounded in the source text. It organizes 3,653 governance documents while preserving page and edition, then uses bounded iterative search to retrieve evidence and verify statements. On 360 questions requiring document discovery, macro recall was 83.0%, compared with 80.5% for the strongest baseline and 73.7% without iterative search; performance was 99.1% when documents were fixed. In a study of 24 participants unfamiliar with two AI bills, most proposed changes focused on how provisions would apply. Participants selected explanation lenses, but citations signaled grounding and rarely prompted source checking. These findings are from the supplied abstract and excerpt.

## Source excerpt

arXiv:2611.17564v1 Announce Type: new Abstract: Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question them. We introduce AI-Voyager, a public-interest system for human-AI civic reasoning, in which people and AI work together to understand, contest and shape the rules that govern AI. A resident can find their city's rules on AI in hiring or upload their country's AI strategy, read it as an affected worker would, open the passage behind any answer, and draft a revision. Its architecture turns 3,653 governance documents from city, state, federal and national governments into passages that keep their page and edition, and retrieves evidence through bounded agentic search that verifies each statement. On 360 new questions that require finding the relevant documents, it reached 83.0% macro recall, against 80.5% for the strongest baseline, 73.7% without iterative search and 99.1% on a benchmark with fixed documents. In a study with 24 participants new to two AI bills, most proposed changes asked how provisions would apply. Participants chose lenses for the kind of explanation they wanted, and citations signaled grounding but rarely led them to check the source. By binding AI assistance to the exact text of public documents, this work introduces a grammar of operations and a design space that inform how such systems are designed and evaluated, and how people take part in governing AI.