XuQixin PRO

Racktic's activity

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

upvoted 2 papers 2 days ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published 5 days ago • 102

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

Paper • 2607.05382 • Published 10 days ago • 83

updated a model 11 days ago

Racktic/alchemy-qwen3-ckpt

Updated 10 days ago

updated a dataset 24 days ago

Racktic/alchemy-eval-logs

Updated 24 days ago • 2.82k

published a model 28 days ago

Racktic/alchemy-qwen3-ckpt

Updated 10 days ago

published a dataset about 1 month ago

Racktic/alchemy-eval-logs

Updated 24 days ago • 2.82k

authored a paper about 1 month ago

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

Paper • 2606.00408 • Published May 29 • 65

upvoted 2 papers about 2 months ago

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

Paper • 2606.02373 • Published Jun 1 • 60

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

Paper • 2606.00408 • Published May 29 • 65

published a dataset 2 months ago

Racktic/DeepSearch-Attn

Updated May 6 • 1.71k

authored a paper 2 months ago

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Paper • 2605.08678 • Published May 9 • 9

upvoted 2 papers 2 months ago

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Paper • 2605.08678 • Published May 9 • 9

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published May 3 • 127

updated a dataset 2 months ago

Racktic/DeepSearch-Attn

Updated May 6 • 1.71k

updated a dataset 3 months ago

Racktic/dsgym_backup

Updated Apr 23 • 50

updated a model 3 months ago

Racktic/DSGym-models

Updated Apr 13

published a model 3 months ago

Racktic/DSGym-models

Updated Apr 13

published a dataset 3 months ago

Racktic/dsgym_backup

Updated Apr 23 • 50

upvoted a paper 4 months ago

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Paper • 2603.20278 • Published Mar 17 • 101

liked a dataset 4 months ago

TIGER-Lab/mle-bench

Updated Aug 2, 2025 • 716 • 1