In-the-Flow Agentic System Optimization for Effective Planning and Tool Use Paper • 2510.05592 • Published Oct 7, 2025 • 106
Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning Paper • 2509.22824 • Published Sep 26, 2025 • 20
VideoScore2: Think before You Score in Generative Video Evaluation Paper • 2509.22799 • Published Sep 26, 2025 • 25
A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports Paper • 2510.02190 • Published Oct 2, 2025 • 18
VideoScore2: Think before You Score in Generative Video Evaluation Paper • 2509.22799 • Published Sep 26, 2025 • 25
VideoScore2: Think before You Score in Generative Video Evaluation Paper • 2509.22799 • Published Sep 26, 2025 • 25
Zero-Shot Long-Form Video Understanding through Screenplay Paper • 2406.17309 • Published Jun 25, 2024 • 1
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations Paper • 2504.00824 • Published Apr 1, 2025 • 43
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs Paper • 2505.20139 • Published May 26, 2025 • 19
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use Paper • 2509.01055 • Published Sep 1, 2025 • 76
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use Paper • 2509.01055 • Published Sep 1, 2025 • 76
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use Paper • 2509.01055 • Published Sep 1, 2025 • 76
VerlTool/pixel_reasoner-7b-grpo-n8-b128-t1.0-lr1e-6-complex-reward-new_global_step_50 8B • Updated Aug 25, 2025 • 4
VerlTool/deepsearch-qwen_qwen3-8b-grpo-n16-b128-t1.0-lr1e-6-new_global_step_70 8B • Updated Aug 25, 2025 • 4
VerlTool/pixel_reasoner-7b-grpo-n8-b128-t1.0-lr1e-6-complex-reward-new_global_step_50 8B • Updated Aug 25, 2025 • 4
VerlTool/deepsearch-qwen_qwen3-8b-grpo-n16-b128-t1.0-lr1e-6-new_global_step_70 8B • Updated Aug 25, 2025 • 4