Skip to content
Review

Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descent

Jul 2026 · arXiv.org · Vol abs/2607.28691 · 0 citations · 19 references
Computer Science

TL;DR

The OurArk architecture for persistent personal agents centered on an agent-owned software body: an identity-bearing, inspectable, and versioned artifact under human custody that provides a concrete substrate for personal agents that people can possess, govern, specialize, and evolve over time.

Abstract

Personalized AI agents are often configurable without giving users control over the artifacts that determine their future behavior. We present OurArk, an architecture for persistent personal agents centered on an agent-owned software body: an identity-bearing, inspectable, and versioned artifact under human custody. The body contains behavior-defining code, prompts, tools, skills, policies, tests, and evolution mechanisms. Memories and credentials remain private instance state, while model inference is treated as a replaceable external service. OurArk defines governed self-evolution and recursive descent over the same body. Self-evolution produces isolated candidate changes that are validated, reviewed, and merged under human control, enabling human-agent co-development of the agent's software body. Descent creates an independently versioned descendant with a distinct identity, mission, history, and fresh private-state boundary; compatible descendants can themselves source further descent. After divergence, direct-parent changes and peer skills can be inspected for selective local adaptation. We implement the architecture in the open-source Genesis creation engine and Enoch reference agent. A four-agent, three-descent linear lineage and executable regression tests demonstrate recursive creation, inherited validation contracts, isolated body changes, human-controlled review, and failed-update recovery. OurArk provides a concrete substrate for personal agents that people can possess, govern, specialize, and evolve over time.

View source

Similar papers

Preprint Aug 2026

Persistent Recursive Worlds Enable Autonomous Software Evolution

Results show that long-horizon software development can be organized around a persistent project rather than a persistent agent, and EvoX Genesis is introduced, which instead makes the software project persistent while allowing local agents to remain finite-lived.

Beichen Huang, Zhenyu Liang, Bowen Zheng et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers

A runtime-independent architecture for persistent agents with six continuity invariants and a quiesce--checkpoint--validate--bind--rehydrate--resume protocol is presented and Enoch realizes the design as a reusable body plus private installed identity, memory, workflow state, and continuation authority.

Zhe Zhao, Roy Zhao Independent Researcher, P. G. A. S. O. C. ScienceEngineering et al. · 2 citations · ⚡1
Jul 2026

LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans

This work introduces logos, a pluggable layer for self-evolution and governance that strengthens existing multiagent frameworks rather than replacing them, and provides a living logic for accountable automation.

Yuma Ichikawa, Yamato Arai, Kosaku Kimura et al. · 0 citations
Review Aug 2026

Self-Evolving Coding Agents

This survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems.

Hao Zhou, Hai-Chuan Hu, Tianyu Luo et al. · 0 citations
Preprint Aug 2026

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

Agent Gym is introduced, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop and introduces the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency.

Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge et al. · 0 citations
Review Sep 2026

Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software Engineering

An open-source Python implementation over XMTP with 1.8-2.9 s cross-continent hot-reconnect latency, and a software-engineering case study in which three agents coordinate a pull-request review while each retains ownership of its proprietary analysis prompts are provided.

Zi-Wei Zhao, Yu Gu, Haofeng Liang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.