SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research Paper • 2606.09730 • Published Jun 8 • 56
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation Paper • 2607.15686 • Published 7 days ago • 15
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Paper • 2607.15257 • Published 8 days ago • 69
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published 15 days ago • 86
Information-Aware KV Cache Compression for Long Reasoning Paper • 2606.26875 • Published 29 days ago • 12
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity Paper • 2607.00248 • Published 24 days ago • 32
TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents Paper • 2606.28480 • Published 28 days ago • 48
Agentic Abstention: Do Agents Know When to Stop Instead of Act? Paper • 2606.28733 • Published 27 days ago • 149
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Paper • 2607.08768 • Published 15 days ago • 34
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published 14 days ago • 83
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation Paper • 2606.26907 • Published 29 days ago • 49
Qwen-AgentWorld: Language World Models for General Agents Paper • 2606.24597 • Published about 1 month ago • 152
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch Paper • 2606.10728 • Published Jun 9 • 34
Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions Paper • 2606.09076 • Published Jun 8 • 66
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents Paper • 2606.02031 • Published Jun 1 • 21