ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents Paper • 2609.17523 • Published 2 days ago • 17
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence Paper • 2609.15973 • Published 3 days ago • 26
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Paper • 2608.25593 • Published 22 days ago • 117
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses Paper • 2608.24876 • Published 23 days ago • 30
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation Paper • 2511.09611 • Published Nov 12, 2025 • 72
Demystifying Reinforcement Learning in Agentic Reasoning Paper • 2510.11701 • Published Oct 13, 2025 • 34