Reasoning Reading CARFT：Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
Agent Reading Memory-R1：Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
LLM-RL Reading From Trial-and-Error to Improvement：A Systematic Analysis of LLM Exploration Mechanisms in RLVR
Agent Reading Chain-of-Agents：End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL