E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation Paper • 2608.30730 • Published 19 days ago • 17
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals Paper • 2607.11505 • Published Jul 13 • 13
Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs Paper • 2607.03936 • Published Jul 4 • 3
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams Paper • 2606.21337 • Published Jun 19 • 23