AI Paper Atlas

Research map / Large language models / Agents, code and math

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution

Robert Tjarko Lange, Yuki Imajuku, Edoardo Cetin

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use weighted parent sampling instead of hill climbing or best-of-N (ablation)ShinkaEvolve · circle packing, AIME, ALE-Bench, MoEsearch performanceImproved
use bandit-based LLM ensemble selection instead of a single LLM or fixed ensemble (ablation)ShinkaEvolve · ablation taskssearch performanceImproved
add embedding-based code novelty rejection sampling (ablation)ShinkaEvolve · ablation taskssearch performanceImproved
add LLM-as-a-novelty-judge on top of embedding filtering (ablation)ShinkaEvolve · ablation taskssearch performanceNo clear effect
evolve ALE-Agent solution with ShinkaEvolveALE-Agent · ALE-Bench LITEaverage score: approximately 2.3%Improved
evolved MoE load balancing loss with extra under-used-expert regularizerglobal-batch LBL (2.7B MoE) · fineweb perplexity and 7 downstream tasksperplexity / accuracyImproved
evaluate top-5 public solutions on private set (ablation)ShinkaEvolve ALE-Bench · ALE-Bench LITEaverage score: 1923.5 -> 1927.0No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy