Yulai Zhao

sarosavo's activity

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

upvoted 13 papers 1 day ago

Reinforcement Learning for Self-Improving Agent with Skill Library

Paper • 2512.17102 • Published 22 days ago • 32

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

Paper • 2512.19673 • Published 18 days ago • 61

Step-DeepResearch Technical Report

Paper • 2512.20491 • Published 17 days ago • 81

LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics

Paper • 2512.21010 • Published 16 days ago • 3

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models

Paper • 2512.19995 • Published 17 days ago • 15

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards

Paper • 2512.21625 • Published 15 days ago • 3

Training AI Co-Scientists Using Rubric Rewards

Paper • 2512.23707 • Published 11 days ago • 18

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 9 days ago • 230

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Paper • 2512.24615 • Published 9 days ago • 103

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Paper • 2601.00423 • Published 8 days ago • 8

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners

Paper • 2601.02996 • Published 3 days ago • 4

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

Paper • 2512.23412 • Published 11 days ago • 36

SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

Paper • 2512.22334 • Published 14 days ago • 33

upvoted 7 papers 17 days ago

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

Paper • 2512.19682 • Published 18 days ago • 15

Meta-RL Induces Exploration in Language Agents

Paper • 2512.16848 • Published 22 days ago • 10

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

Paper • 2512.17008 • Published 22 days ago • 10

Are We on the Right Way to Assessing LLM-as-a-Judge?

Paper • 2512.16041 • Published 22 days ago • 32

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

Paper • 2512.17260 • Published 21 days ago • 48

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Paper • 2512.16969 • Published 22 days ago • 111

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image

Paper • 2512.16899 • Published 22 days ago • 12