Young-Jun Lee PRO

passing2961's activity

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

upvoted 3 papers 2 days ago

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

Paper • 2606.13662 • Published 4 days ago • 26

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Paper • 2606.13681 • Published 4 days ago • 127

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published 4 days ago • 86

upvoted a paper 4 days ago

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Paper • 2606.11042 • Published 6 days ago • 20

upvoted 2 papers 5 days ago

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Paper • 2606.07297 • Published 10 days ago • 110

Agents' Last Exam

Paper • 2606.05405 • Published 12 days ago • 335

upvoted 3 papers 6 days ago

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Paper • 2606.05806 • Published 11 days ago • 22

OpenSkill: Open-World Self-Evolution for LLM Agents

Paper • 2606.06741 • Published 11 days ago • 27

GENEB: Why Genomic Models Are Hard to Compare

Paper • 2606.04525 • Published 12 days ago • 46

upvoted 3 papers 9 days ago

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Paper • 2606.06473 • Published 11 days ago • 19

AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints

Paper • 2606.05622 • Published 11 days ago • 40

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Paper • 2606.04743 • Published 12 days ago • 44

upvoted 2 papers 10 days ago

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

Paper • 2606.01286 • Published 15 days ago • 5

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Paper • 2606.05080 • Published 12 days ago • 30

upvoted a paper 12 days ago

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Paper • 2606.02404 • Published 14 days ago • 56

upvoted 5 papers 17 days ago

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published 18 days ago • 77

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

Paper • 2605.28655 • Published 19 days ago • 12

ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations

Paper • 2605.27908 • Published 19 days ago • 6

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Paper • 2605.28775 • Published 19 days ago • 38

ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

Paper • 2605.26340 • Published 21 days ago • 36