Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 4 days ago • 16
LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4 Paper • 2607.15509 • Published Aug 18
An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism Paper • 2607.15511 • Published Aug 10