IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse Paper • 2603.12201 • Published Mar 12 • 54
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards Paper • 2601.06021 • Published Jan 9 • 48
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices Paper • 2512.01374 • Published Dec 1, 2025 • 107
