paper-with-me

Papers

Persistent Recursive Worlds Enable Autonomous Software Evolution

2026-08-12 · Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng hf

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 used DeepSeek V4 Flash to 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 with GLM 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.

📄 PDF Abstract BibTeX arXiv:2608.10450

Code (3)

Aaron617/agent-arXiv-daily ★ 10
EMI-Group/genesis ★ 13
Valiant-Cat/hfpaper

Similar Papers 제목 키워드 기반

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

2026-09-10 · Yi Duan, Ying Liu, Zirui Tang, Haodong Chen 외 arxiv

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Ind…

Planetary Exploration 3.0: A Roadmap for Software-Defined, Radically Adaptive Space Systems

2026-04-22 · Masahiro Ono, Daniel Selva, Morgan L. Cable, Marie Ethvignot 외 arxiv

The surface and subsurface of worlds beyond Mars remain largely unexplored. Yet these worlds hold keys to fundamental questions in planetary science - from potentially habitable subsurface oceans on icy moons to ancient …

Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs

2026-09-10 · Zhiqi Li, Yuxuan Liao, Bo Zhu hf

Code world models represent worlds as executable programs, but this representation alone does not determine how to construct a complex world. We introduce Recursive Code World Models (RCWM), a framework for reconstructin…

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

2026-05-19 · Jinbiao Wei, Qianran Ma, Yilun Zhao, Xiao Zhou 외 arxiv

We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured…

Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems

2026-09-15 · Deepak Akkil, Tamer Abuelsaad, Karthik Vikram, Matthew Pace 외 hf

As AI agents move from bounded tasks to persistent deployments, failures can propagate through memory, tools, other agents, and environmental state long after their interactions. This creates a safety regime that cannot …