wongyukim

wongyukim's activity

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

upvoted 3 papers 1 day ago

SkillGrad: Optimizing Agent Skills Like Gradient Descent

Paper • 2605.27760 • Published 5 days ago • 23

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Paper • 2605.26302 • Published 6 days ago • 27

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 4 days ago • 356

upvoted 4 papers 3 days ago

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

Paper • 2605.27295 • Published 5 days ago • 17

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Paper • 2605.27366 • Published 5 days ago • 19

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

Paper • 2605.25979 • Published 6 days ago • 24

HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness

Paper • 2605.02396 • Published 27 days ago • 24

upvoted 3 papers 4 days ago

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Paper • 2605.23986 • Published 15 days ago • 17

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

Paper • 2605.26086 • Published 6 days ago • 22

Foundation Protocol: A Coordination Layer for Agentic Society

Paper • 2605.23218 • Published 9 days ago • 75

upvoted 4 papers 5 days ago

SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

Paper • 2605.22878 • Published 11 days ago • 56

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

Paper • 2605.23899 • Published 9 days ago • 28

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published 9 days ago • 204

Your Embedding Model is SMARTer Than You Think

Paper • 2605.24938 • Published 7 days ago • 24

upvoted 2 papers 9 days ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published 11 days ago • 12

IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools

Paper • 2605.20682 • Published 11 days ago • 83

upvoted 4 papers 10 days ago

Harnessing LLM Agents with Skill Programs

Paper • 2605.17734 • Published 13 days ago • 34

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Paper • 2605.18703 • Published 13 days ago • 48

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Paper • 2605.20025 • Published 12 days ago • 185

Active Learners as Efficient PRP Rerankers

Paper • 2605.14236 • Published 16 days ago • 98