Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals Paper • 2607.11505 • Published 22 days ago • 18
InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models Paper • 2510.11341 • Published Oct 13, 2025 • 37
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks Paper • 2510.08002 • Published Oct 9, 2025 • 24