Paper

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

Unreadunread

AI summary

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?

Reading status

Priority

About this paper

Authors: Can Gurkan, Forrest Stonedahl, Uri Wilensky
Released: 2026-06-06 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, word, class, circle, source, line, rate, without. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2606.05408

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.