Zhiyuan Ning

nzynzy's activity

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

upvoted 4 papers 7 days ago

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

Paper • 2601.10402 • Published 9 days ago • 36

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Paper • 2601.09667 • Published 9 days ago • 82

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Paper • 2601.08763 • Published 10 days ago • 140

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning

Paper • 2601.07641 • Published 12 days ago • 44

upvoted 16 papers 8 days ago

Can We Predict Before Executing Machine Learning Agents?

Paper • 2601.05930 • Published 14 days ago • 26

SimpleMem: Efficient Lifelong Memory for LLM Agents

Paper • 2601.02553 • Published 18 days ago • 37

AgentOCR: Reimagining Agent History via Optical Self-Compression

Paper • 2601.04786 • Published 16 days ago • 28

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published 15 days ago • 29

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

Paper • 2601.05808 • Published 15 days ago • 36

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

Paper • 2601.05593 • Published 15 days ago • 79

Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits

Paper • 2512.20578 • Published Dec 23, 2025 • 82

Controlled Self-Evolution for Algorithmic Code Optimization

Paper • 2601.07348 • Published 12 days ago • 110

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Paper • 2601.02151 • Published 19 days ago • 101

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published 15 days ago • 203

Recursive Language Models

Paper • 2512.24601 • Published 24 days ago • 73

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

Paper • 2512.17260 • Published Dec 19, 2025 • 50

Guided Self-Evolving LLMs with Minimal Human Supervision

Paper • 2512.02472 • Published Dec 2, 2025 • 53

How Far Are We from Genuinely Useful Deep Research Agents?

Paper • 2512.01948 • Published Dec 1, 2025 • 56

When Reasoning Meets Its Laws

Paper • 2512.17901 • Published Dec 19, 2025 • 60

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Paper • 2512.19673 • Published Dec 22, 2025 • 63