Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Paper • 2606.31825 • Published Jun 30 • 26
CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents Paper • 2603.15421 • Published Apr 20 • 24
User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale Paper • 2601.08225 • Published Jan 13 • 53
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training Paper • 2509.25758 • Published Sep 30, 2025 • 25
CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction Paper • 2508.03159 • Published Aug 5, 2025 • 23
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models Paper • 2506.19697 • Published Jun 24, 2025 • 45
