Skip to content
AI News HubLIVE
Original source2 min read

Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents

Summary

Agentao is a new arXiv paper proposing a governed, local-first runtime for tool-using LLM agents. It separates model-generated action proposals from host-authorized execution, making permissions, state, protocol boundaries, and execution traces explicit runtime abstractions through a layered architecture with a permission-mediated tool system, memory, replay, plugins, skills, and sub-agents. The authors stress that the work offers no formal safety guarantees, aiming instead at more governable and inspectable agents for host-controlled local environments.

SourcearXiv AIAuthor: Bo Jin, Qiang Jiao, Xin Tong
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 4 Jul 2026]

Title:Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents

View a PDF of the paper titled Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents, by Bo Jin and 2 other authors

View PDF HTML (experimental)

Abstract:LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols. These capabilities make agents useful, but they also introduce risks related to over-privileged actions, weak auditability, prompt injection, tool poisoning, and uncontrolled side effects. This paper presents Agentao, a governed local-first runtime for tool-using LLM agents. Agentao separates model-generated action proposals from host-authorized execution through a layered architecture consisting of host-facing surfaces, a host contract, a runtime core, a permission-mediated tool system, and supporting subsystems for memory, replay, plugins, skills, sub-agents, and protocol integration. We describe the motivation, threat model, design goals, governance model, execution pipeline, and structured event interface of the system. Agentao does not provide formal safety guarantees; rather, it demonstrates how permissions, state, protocol boundaries, and execution traces can be made explicit runtime abstractions for building agents that are more governable, inspectable, and suitable for host-controlled local environments. The code is publicly available at this https URL.

Comments: The code is publicly available at Github. We are conducting testing and analysis of this framework, and will provide experimental results and examples in future versions

Subjects:

Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)

Cite as: arXiv:2608.13574 [cs.AI]

(or arXiv:2608.13574v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.13574

arXiv-issued DOI via DataCite

Submission history

From: Bo Jin [view email] [v1] Sat, 4 Jul 2026 10:37:01 UTC (142 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents, by Bo Jin and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-08

Change to browse by:

cs cs.MA

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Separates model-generated action proposals from host-authorized execution
  • Uses a layered architecture: host-facing surfaces, host contract, runtime core, permission-mediated tool system, and support subsystems
  • Targets over-privileged actions, weak auditability, prompt injection, tool poisoning, and uncontrolled side effects
  • Offers no formal safety guarantees; code is public on GitHub with experiments promised in later versions

Highlights and analysis are generated automatically and may contain errors. Check the original source.