2 papers
cs.AI2026
Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
Cen Mia Zhao, Haibo Ruan, Wenjie Chen +3
LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state handling, and recovery logic.…
cs.AI2026
Agentic ML Exploration (A-MLE) for Ads Ranking
Erwin Gao, Vinodh Kumar Sunkara, Jingyi Guan +36
Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research,…