π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 99
Young-Jun Lee PRO
passing2961
AI & ML interests
Social Dialogue System, Multi-Modal Dialogue
Recent Activity
upvoted a paper 1 day ago
Self-Improving CAD Generation Agents with Finite Element Analysis as FeedbackOrganizations
upvoted 4
papers 1 day ago
Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback
Paper • 2605.17448 • Published • 17
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
Paper • 2605.23345 • Published • 12
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
Paper • 2605.23204 • Published • 25
updated a
collection 4 days ago
upvoted a paper 4 days ago
upvoted 5
papers 6 days ago
Code as Agent Harness
Paper • 2605.18747 • Published • 206
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
Paper • 2605.18703 • Published • 48
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 57
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 182
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists
Paper • 2605.20668 • Published • 11
upvoted 4
papers 12 days ago
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
Paper • 2605.14445 • Published • 20
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 45
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
Paper • 2605.13301 • Published • 157
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 110
upvoted a paper 15 days ago