DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment Paper • 2607.07820 • Published 17 days ago • 88
Environment-free Synthetic Data Generation for API-Calling Agents Paper • 2607.16900 • Published 7 days ago • 20
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune Paper • 2607.18213 • Published 5 days ago • 75
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published 9 days ago • 99
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published 9 days ago • 168
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation Paper • 2607.11886 • Published 12 days ago • 84
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published 11 days ago • 108
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published 16 days ago • 87
Scalable Visual Pretraining for Language Intelligence Paper • 2607.09657 • Published 15 days ago • 56
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published 16 days ago • 74
Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing Paper • 2607.07953 • Published 17 days ago • 15
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Paper • 2607.08768 • Published 16 days ago • 34
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation Paper • 2607.08758 • Published 16 days ago • 40
Video-Oasis: Rethinking Evaluation of Video Understanding Paper • 2603.29616 • Published 23 days ago • 65