Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper
• 2506.01939 • Published
• 188
LLM RL
-
-
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
Paper • 2511.21689 • Published • 125 -
PretrainZero: Reinforcement Active Pretraining
Paper • 2512.03442 • Published • 48 -
DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
Paper • 2601.16344 • Published • 11 -
SkillOrchestra: Learning to Route Agents via Skill Transfer
Paper • 2602.19672 • Published • 55 -
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
Paper • 2602.23166 • Published • 40