深度搜索Agent Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction Paper • 2604.27221 • Published 8 days ago • 32
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction Paper • 2604.27221 • Published 8 days ago • 32
LLM RL Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 190 ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper • 2511.21689 • Published Nov 26, 2025 • 126 PretrainZero: Reinforcement Active Pretraining Paper • 2512.03442 • Published Dec 3, 2025 • 50 DSGym: A Holistic Framework for Evaluating and Training Data Science Agents Paper • 2601.16344 • Published Jan 22 • 12
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 190
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper • 2511.21689 • Published Nov 26, 2025 • 126
DSGym: A Holistic Framework for Evaluating and Training Data Science Agents Paper • 2601.16344 • Published Jan 22 • 12
深度搜索Agent Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction Paper • 2604.27221 • Published 8 days ago • 32
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction Paper • 2604.27221 • Published 8 days ago • 32
LLM RL Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 190 ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper • 2511.21689 • Published Nov 26, 2025 • 126 PretrainZero: Reinforcement Active Pretraining Paper • 2512.03442 • Published Dec 3, 2025 • 50 DSGym: A Holistic Framework for Evaluating and Training Data Science Agents Paper • 2601.16344 • Published Jan 22 • 12
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 190
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Paper • 2511.21689 • Published Nov 26, 2025 • 126
DSGym: A Holistic Framework for Evaluating and Training Data Science Agents Paper • 2601.16344 • Published Jan 22 • 12
