Search papers, labs, and topics across Lattice.
The paper introduces EvoX Genesis, a novel framework for autonomous software evolution that allows finite-lived agents to contribute to a persistent software project by organizing development around a persistent recursive world. This approach enables local agents to propose changes while maintaining a continuous project history, demonstrated through the successful development of a Rust-based C compiler and the reimplementation of MESA modules. Key results include achieving significant performance improvements and maintaining test performance across agent replacements, highlighting a shift in how software development can be structured over long timescales.
Long-horizon software development can thrive without relying on persistent agents, as demonstrated by Genesis's ability to evolve complex systems through finite-lived contributors.
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.
