{"ID":3084668,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-06T20:20:29.47808685Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05408","arxiv_id":"2606.05408","title":"Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution","abstract":"When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? We study this question by analyzing LLM-driven mutation chains in the absence of selection pressure within a domain-specific language, varying prompt design, model family, and stochastic replication. We find that LLM-based mutation consistently converges toward restricted attractor regions in program space. Convergence is especially severe at the structural level: in 87% of chains, over 93% of mutations revisit a previously seen structural form, with most variation confined to terminal substitutions within recurring templates. Cycle analysis reveals short cycles and self-loops dominating the transition structure. The rate of convergence varies with prompt wording and model choice, but the phenomenon is robust across conditions. A classical GP subtree mutation operator does not exhibit comparable convergence, suggesting that the effect is intrinsic to the LLM mutation pipeline. These findings reveal a tension at the heart of LLM-driven program evolution: the same capabilities that enable semantics-aware program transformation also carry a systematic bias toward structural homogeneity that must be accounted for if such systems are to sustain open-ended exploration. Source code is available at https://github.com/can-gurkan/lmca.","short_abstract":"When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? We study this question by analyzing LLM-driven mutation chains in the absence of selection pressure within a domain-specific language, varying prompt design, model family, and stochastic replication. We find that LLM-ba...","url_abs":"https://arxiv.org/abs/2606.05408","url_pdf":"https://arxiv.org/pdf/2606.05408v1","authors":"[\"Can Gurkan\",\"Forrest Stonedahl\",\"Uri Wilensky\"]","published":"2026-06-03T20:22:29Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.NE\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":612853,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-05T06:46:15.197025399Z","DeletedAt":null,"paper_id":3084668,"paper_url":"https://arxiv.org/abs/2606.05408","paper_title":"Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution","repo_url":"https://github.com/can-gurkan/lmca","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}