arXiv:2606. 05408v1 Announce Type: new Abstract: When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones?
Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space. Syntactic edit size is an unreliable proxy: a small code change can alter nearly every action, while a larger rewrite can preserve the same execution trace.
arXiv:2608. 10196v1 Announce Type: cross Abstract: Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space.
arXiv:2606. 26173v1 Announce Type: new Abstract: Recent work shows that Large Language Models (LLMs) can act as semantic mutation operators for the evolutionary discovery of programs and proofs.
Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks and domains. However, existing LLM-driven evolutionary frameworks largely discard such knowledge, repeatedly rediscovering similar ideas and limiting opportunities for cross-run and cross-task learning.
arXiv:2608. 10795v1 Announce Type: new Abstract: Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related tasks and domains.
arXiv:2608. 07645v1 Announce Type: new Abstract: Self-improving coding agents that iteratively rewrite their own source code have demonstrated impressive performance on coding tasks.
arXiv:2608. 05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.
The paper demonstrates that large language models can generate executable procedural content generators, enabling direct search over generator programs rather than individual levels. Using Sokoban, Zelda, Dangerous Dave, and Lode Runner, the authors evolve complete Python generators via language‑model mutation and crossover, and introduce Continual Abstraction Discovery (CAD) to extract reusable primitives into a run‑specific helper module. Experiments show that CAD consistently improves mean final best fitness across all domain and API comparisons, with learned libraries being adopted by subsequent programs and repeatedly rediscovering useful utilities.
arXiv:2608. 19854v1 Announce Type: cross Abstract: Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture.
arXiv:2510.14980v3 Announce Type: replace Abstract: Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate pro...
arXiv:2607. 05666v1 Announce Type: cross Abstract: AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change.
arXiv:2606. 15943v1 Announce Type: cross Abstract: Engineering LLM-native software remains a challenging and immature field.