EvoSkillRec evolves recommender architectures from reusable 'skill genomes'
_reachsumit · x · 2026-09-29
EvoSkillRec decomposes recommender models into atomic executable skills with typed I/O, semantic annotations, and code, representing architectures as typed skill genomes. It evolves models in two coupled spaces: a constrained skill-space that mutates, recombines, and reuses validated skills, plus an open-ended code-space where LLM planners invent new modules guided by evolution traces. The framework addresses the invalid edits and lost design knowledge of unconstrained LLM-driven code evolution via a promotion-and-reuse mechanism.
More from Research
- New OCR leaderboard tests 14 open models on 2,165 historical pages; best hits 97.6% accuracy under $2 per 1k pages — IgorCarron · 2026-10-24
- Wavestone reverse-engineers 11 coding agents, maps the same 7-part harness inside all of them — blaizedsouza · 2026-10-24
- Looped Transformers heat up: 10 new papers on recurrent loop architectures — TheTuringPost · 2026-10-24
- FormalizeSampling: Sampling and diffusion convergence theorems machine-checked in Lean 4 — TianbaoX · 2026-10-24
- Alison Gopnik: What Kids Are 'Bad' At May Be Features, Not Flaws — AlisonGopnik · 2026-10-24
- Explicit Diophantine equation provably equivalent to Con(ZFC) constructed, Lean proof in progress — IgorCarron · 2026-10-24