[Paper] Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution

Published: (June 3, 2026 at 04:22 PM EDT)
2 min read
Source: arXiv

Source: arXiv - 2606.05408v1

Overview

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.

Key Contributions

This paper presents research in the following areas:

  • cs.AI
  • cs.NE

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.AI.

Authors

  • Can Gurkan
  • Forrest Stonedahl
  • Uri Wilensky

Paper Information

  • arXiv ID: 2606.05408v1
  • Categories: cs.AI, cs.NE
  • Published: June 3, 2026
  • PDF: Download PDF
0 views
Back to Blog

Related posts

Read more »