Yaorui SHI

yrshi's activity

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

upvoted a paper 4 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 9 days ago • 56

upvoted 3 papers 5 days ago

EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents

Paper • 2610.13021 • Published 16 days ago • 76

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 6 days ago • 177

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 16 days ago • 123

upvoted a paper 10 days ago

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Paper • 2610.12233 • Published 17 days ago • 30

upvoted a paper 19 days ago

PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins

Paper • 2609.32423 • Published 29 days ago • 11

upvoted a paper about 1 month ago

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Paper • 2609.23986 • Published Sep 21 • 31

upvoted 2 papers about 2 months ago

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

Paper • 2608.27456 • Published Aug 27 • 84

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published Aug 26 • 115

upvoted a paper 2 months ago

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

Paper • 2608.20202 • Published Aug 20 • 35

upvoted 10 papers 3 months ago

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published Aug 3 • 32

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 105

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

Paper • 2607.25308 • Published Jul 28 • 42

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published Jul 29 • 29

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

Paper • 2607.27616 • Published Jul 30 • 41

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

Paper • 2607.27816 • Published Jul 30 • 35

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

Paper • 2607.26497 • Published Jul 30 • 54

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

Paper • 2607.18217 • Published Jul 20 • 64

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

Paper • 2607.05382 • Published Jul 9 • 83

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

Paper • 2607.11886 • Published Jul 13 • 78