What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems Paper • 2606.05304 • Published Jun 3 • 5
PEAR: Phase Entropy Aware Reward for Efficient Reasoning Paper • 2510.08026 • Published Oct 9, 2025 • 9
Through the Valley: Path to Effective Long CoT Training for Small Language Models Paper • 2506.07712 • Published Jun 9, 2025 • 18