Xirui Li PRO

AIcell's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Paper • 2512.24873 • Published Dec 31, 2025 • 109

upvoted 2 papers 3 days ago

Co-Evolving Policy Distillation

Paper • 2604.27083 • Published 5 days ago • 46

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published 5 days ago • 47

upvoted a paper 11 days ago

AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation

Paper • 2604.18240 • Published 14 days ago • 15

upvoted a paper 12 days ago

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

Paper • 2604.18543 • Published 14 days ago • 27

upvoted a paper 13 days ago

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Paper • 2604.18292 • Published 14 days ago • 82

upvoted a paper 16 days ago

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 19 days ago • 117

upvoted a paper 19 days ago

CocoaBench: Evaluating Unified Digital Agents in the Wild

Paper • 2604.11201 • Published 21 days ago • 36

upvoted a paper 20 days ago

FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios

Paper • 2604.07413 • Published 26 days ago • 95

upvoted 2 papers 21 days ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published 25 days ago • 261

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 26 days ago • 323

upvoted a paper 22 days ago

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Paper • 2602.22766 • Published Feb 26 • 44

upvoted a paper 24 days ago

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published 27 days ago • 66

upvoted 6 papers 25 days ago

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Paper • 2604.04901 • Published 28 days ago • 40

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published 28 days ago • 235

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

Paper • 2604.05172 • Published 28 days ago • 24

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Paper • 2604.04323 • Published 28 days ago • 41

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation

Paper • 2604.03922 • Published 29 days ago • 53

Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents

Paper • 2604.06132 • Published 27 days ago • 119

upvoted a paper 26 days ago

ClawArena: Benchmarking AI Agents in Evolving Information Environments

Paper • 2604.04202 • Published 29 days ago • 37