Lei Wang

demolei's activity

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

upvoted a paper about 21 hours ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published 14 days ago • 445

upvoted a paper 1 day ago

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

Paper • 2608.15763 • Published 7 days ago • 43

upvoted 2 papers 3 days ago

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Paper • 2608.23041 • Published 5 days ago • 60

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

Paper • 2608.24876 • Published 4 days ago • 23

upvoted a paper 4 days ago

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Paper • 2608.23035 • Published 5 days ago • 41

liked a model 4 days ago

apodex/Apodex-1.1-mini

Text Generation • 36B • Updated 3 days ago • 1.31k • 101

upvoted a paper 4 days ago

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 5 days ago • 200

upvoted a paper 5 days ago

Fara-1.5: Scalable Learning Environments for Computer Use Agents

Paper • 2606.20785 • Published Jun 18 • 9

upvoted a paper 8 days ago

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

Paper • 2608.17393 • Published 11 days ago • 24

upvoted 4 papers 15 days ago

An AI4AI Framework for Visual Token Pruning

Paper • 2608.07193 • Published 22 days ago • 15

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published 16 days ago • 55

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published 29 days ago • 113

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published 22 days ago • 109

upvoted 3 papers 16 days ago

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published 28 days ago • 263

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Paper • 2608.10299 • Published 19 days ago • 135

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Paper • 2608.12307 • Published 17 days ago • 113

upvoted 4 papers 17 days ago

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Paper • 2607.07820 • Published Jul 8 • 94

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published Jul 23 • 154

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published 19 days ago • 761

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 19 days ago • 342