AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search

Zhen Liu, Yuhan Liu, Jinjun Wang, Wei Song, Jianyi Liu, Jingwen Fu

ICML 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 0 citations (OpenAlex)

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 SPARK factor-scoped editing instead of free-form OpenEvolve editsOpenEvolve with DeepSeek-R1 · CLRS DFS (OOD)OOD accuracy (%): 32.54 -> 83.74Improved
use SPARK instead of EvoPrompting, in evaluated candidatesEvoPrompting · CLRS DFSsample efficiency: 28.1x (1600/57 evaluations)Improved
use SPARK on full 30-task CLRS suiteCLRS reference and EvoPrompting · CLRS 30 tasksmean OOD accuracy (%): 75.98 -> 83.91 (EvoPrompting 80.89)Improved
add ASR scope selection to RC+SAR (ablation)SPARK · CLRS DFS (DeepSeek-R1)OOD accuracy (%): 56.79 -> 83.74Improved
add RC+SAR refinement to ASR-only (ablation)SPARK · CLRS DFS (DeepSeek-R1)OOD accuracy (%): 65.28 -> 83.74Improved
ablation components repeated with Qwen-Plus editor (ablation)SPARK · CLRS DFS (Qwen-Plus)OOD accuracy (%): 64.50 -> 80.50Improved
run multi-round evolution instead of a single iteration (ablation)SPARK · CLRS 10-task subsetmean OOD accuracy (%): 72.58 -> 83.92Improved
constrain edits to one factor scope via ASR (ablation)OpenEvolve · CLRS DFS search over 100 attemptscumulative valid rate: 0.25-0.3 -> 0.5-0.6Improved
constrain edits to one factor scope via ASR (ablation)OpenEvolve · CLRS DFS searchentanglement rateImproved
use SPARK instead of OpenEvolve on MNIST-1DOpenEvolve · MNIST-1Daccuracy (%): 70.25 -> 95.99Improved
use SPARK instead of OpenEvolve on CartPole-v1OpenEvolve · CartPole-v1mean test return: 377.55 -> 489.00Improved
use SPARK instead of OpenEvolve on Mice Protein ExpressionOpenEvolve · Mice Protein Expressionaccuracy (%): 61.78 -> 61.78No 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