Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images Paper • 2602.19424 • Published Feb 23 • 6
DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions Paper • 2604.05623 • Published Apr 7 • 1
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published Jun 10 • 128
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence Paper • 2604.18292 • Published Apr 20 • 88
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence Paper • 2604.18292 • Published Apr 20 • 88
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use Paper • 2510.27363 • Published Oct 31, 2025 • 23
SmartSearch: Process Reward-Guided Query Refinement for Search Agents Paper • 2601.04888 • Published Jan 8 • 10
ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration Paper • 2601.06860 • Published Jan 11 • 16
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis Paper • 2601.05808 • Published Jan 9 • 38
CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation Paper • 2505.15145 • Published May 21, 2025 • 1
OJBench: A Competition Level Code Benchmark For Large Language Models Paper • 2506.16395 • Published Jun 19, 2025 • 4
DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving Paper • 2505.20665 • Published May 27, 2025 • 2
MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision Paper • 2508.08177 • Published Aug 11, 2025
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting Paper • 2601.02151 • Published Jan 5 • 115
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting Paper • 2601.02151 • Published Jan 5 • 115