Yaorui SHI

yrshi's activity

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

upvoted a paper about 16 hours ago

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Paper • 2607.25308 • Published 4 days ago • 36

upvoted a paper about 17 hours ago

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published 3 days ago • 25

upvoted 3 papers about 22 hours ago

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

Paper • 2607.27616 • Published 2 days ago • 35

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

Paper • 2607.27816 • Published 2 days ago • 30

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Paper • 2607.26497 • Published 2 days ago • 39

upvoted a paper 11 days ago

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

Paper • 2607.18217 • Published 12 days ago • 59

upvoted 3 papers 16 days ago

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published 23 days ago • 87

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 19 days ago • 84

SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding

Paper • 2607.10400 • Published 21 days ago • 71

upvoted 2 papers 18 days ago

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

Paper • 2601.05808 • Published Jan 9 • 38

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published 23 days ago • 76

upvoted a paper 19 days ago

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Paper • 2607.02255 • Published about 1 month ago • 67

upvoted a collection about 1 month ago

OpenThinker-Agent2

Collection

OpenThinker-Agent2: agentic SFT/RL datasets and 8B/32B models (cold-start SFT, RL, and the OpenThinkerAgent-32B release). • 11 items • Updated Jun 11 • 10

upvoted 2 papers about 1 month ago

DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation

Paper • 2606.26058 • Published Jun 24 • 67

FastContext: Training Efficient Repository Explorer for Coding Agents

Paper • 2606.14066 • Published Jun 12 • 94

upvoted 3 papers about 2 months ago

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published Jun 5 • 75

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 387

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Paper • 2606.04703 • Published Jun 3 • 26

upvoted 2 papers 2 months ago

V_{0.5}: Generalist Value Model as a Prior for Sparse RL Rollouts

Paper • 2603.10848 • Published Mar 11 • 17

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

Paper • 2605.27141 • Published May 26 • 20