Xuying Ning

YennNing's activity

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

upvoted 2 papers 19 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 23 days ago • 49

T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration

Paper • 2605.29054 • Published 25 days ago • 8

upvoted 5 papers about 1 month ago

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

Paper • 2609.38143 • Published Sep 29 • 53

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

Paper • 2609.40111 • Published Sep 30 • 31

Learning from Teacher Continuations at Student States

Paper • 2609.36246 • Published Sep 28 • 34

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published Sep 27 • 34

SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

Paper • 2609.30192 • Published Sep 24 • 8

upvoted a paper about 2 months ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 76

upvoted 2 papers 2 months ago

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published Sep 3 • 112

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 153

upvoted a paper 3 months ago

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

Paper • 2608.12307 • Published Aug 12 • 107

upvoted a paper 4 months ago

Trimming the Long-Tail of Visual World Modeling Evaluation

Paper • 2606.24256 • Published Jun 23 • 31

upvoted a paper 5 months ago

Advancing Creative Physical Intelligence in Large Multimodal Models

Paper • 2605.26396 • Published May 25 • 20

upvoted 5 papers 6 months ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

Paper • 2605.21468 • Published May 20 • 51

Code as Agent Harness

Paper • 2605.18747 • Published May 18 • 195

Useful Memories Become Faulty When Continuously Updated by LLMs

Paper • 2605.12978 • Published May 13 • 19

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Paper • 2605.10899 • Published May 11 • 57

Heterogeneous Scientific Foundation Model Collaboration

Paper • 2604.27351 • Published Apr 30 • 128

upvoted a paper 8 months ago

dLLM: Simple Diffusion Language Modeling

Paper • 2602.22661 • Published Feb 26 • 137

upvoted a paper 10 months ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 206