Persistent Recursive Worlds Enable Autonomous Software Evolution
Summary
Introduces EvoX Genesis, a framework that organizes long-horizon software development around a persistent project rather than persistent agents, enabling autonomous construction of a Rust-based C compiler and reimplementation of MESA numerical modules with low cost and high performance.
View Cached Full Text
Cached at: 08/13/26, 03:33 PM
Paper page - Persistent Recursive Worlds Enable Autonomous Software Evolution
Source: https://huggingface.co/papers/2608.10450
Abstract
Genesis organizes long-horizon software development around a persistent project rather than persistent agents, enabling multi-day compiler construction and numerical module reimplementation with low cost and high performance.
Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis usedDeepSeek V4 Flashto build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated withGLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent.
View arXiv pageView PDFProject pageGitHub12Add to collection
Get this paper in your agent:
hf papers read 2608\.10450
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.10450 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.10450 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.10450 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
EvoMap/evolver
Evolver is a GEP-powered self-evolution engine for AI agents that automates prompt optimization and creates auditable, reusable evolution assets. The project is transitioning from fully open source to source-available while maintaining backward compatibility with existing MIT and GPL-3.0 releases.
@tom_doerr: Semi-autonomous agents optimize codebases through parallel experimentation https://github.com/evo-hq/evo
Evo is an open-source tool that provides semi-autonomous agents to optimize codebases through parallel experimentation, using tree search and multiple subagents to autonomously discover and improve metrics.
MKEvolve: A Modular Multi-Agent Framework for Kernel Code Generation
Presents MKEvolve, a modular multi-agent framework that iteratively co-evolves modular decomposition and LLM-generated kernels for hardware accelerators, achieving improved correctness and speedup over direct synthesis while reducing token usage.
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
Introduces EvolvingWorld, an open-schema framework and benchmark for co-evolving role-play agents and world models in interactive literary worlds, enabling long-horizon simulation with persistent character and world state updates.
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
Ouroboros is a self-developing frontier coding agent whose tools, prompts, and core implementation improve through reviewed commits, achieving state-of-the-art results on Terminal-Bench, OSWorld, and CL-Bench, with a long-running live deployment called Hope.