Junyao

TberiusJunyao's activity

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

upvoted a paper about 19 hours ago

More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents

Paper • 2610.27406 • Published 3 days ago • 8

upvoted a paper about 22 hours ago

CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?

Paper • 2610.25078 • Published 4 days ago • 93

upvoted a paper about 23 hours ago

Harness Self-Evolution for Long-Horizon Terminal Agents

Paper • 2610.27435 • Published 2 days ago • 11

upvoted a paper 6 days ago

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine

Paper • 2610.22192 • Published 7 days ago • 41

upvoted a paper 14 days ago

Self-Supervised Scaling of Terminal Environments for Scientific Domains

Paper • 2610.02710 • Published 20 days ago • 13

upvoted a paper 17 days ago

Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

Paper • 2610.02826 • Published 20 days ago • 106

upvoted a paper 28 days ago

The Past Frames the Future: Memory for Autoregressive Video Generation

Paper • 2609.28466 • Published 29 days ago • 66

upvoted 2 papers about 1 month ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published Sep 11 • 69

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

Paper • 2609.06702 • Published Sep 6 • 26

upvoted a collection about 1 month ago

T1

Collection

CC BY 4.0 RL checkpoints for T1; base-model and third-party terms still apply. • 4 items • Updated Sep 16 • 5

upvoted 2 papers about 1 month ago

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published Sep 10 • 67

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published Sep 3 • 50

upvoted a paper about 2 months ago

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published Aug 24 • 211

upvoted a paper 2 months ago

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

Paper • 2608.15930 • Published Aug 16 • 47

upvoted a collection 3 months ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Collection

CC BY 4.0 datasets and SFT/RL checkpoints for recursive task synthesis; base-model and third-party terms still apply. • 6 items • Updated Aug 10 • 18

upvoted 4 papers 3 months ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published Aug 7 • 252

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Paper • 2607.18722 • Published Jul 21 • 36

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published Jul 14 • 222

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

Paper • 2607.08964 • Published Jul 9 • 79

upvoted a paper 4 months ago

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published Jun 29 • 50