BOOKMARKS: Efficient Active Storyline Memory for Role-playing Paper • 2605.14169 • Published May 13 • 8
Improving Data and Reward Design for Scientific Reasoning in Large Language Models Paper • 2602.08321 • Published Feb 9 • 44
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents Paper • 2602.07274 • Published Feb 6 • 211
MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Paper • 2602.01734 • Published Feb 2 • 34