pangpangxuan

pangxuan's activity

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

upvoted a paper 1 day ago

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 5 days ago • 90

upvoted 2 papers 3 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 5 days ago • 411

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

Paper • 2607.13285 • Published 18 days ago • 230

upvoted a paper 7 days ago

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Paper • 2607.20911 • Published 9 days ago • 26

upvoted a paper 8 days ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published 10 days ago • 31

upvoted a paper 10 days ago

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

Paper • 2607.18722 • Published 11 days ago • 35

upvoted a paper 11 days ago

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Paper • 2606.29538 • Published 16 days ago • 142

upvoted a paper 18 days ago

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

Paper • 2607.08964 • Published 23 days ago • 76

upvoted a paper 30 days ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published Jun 29 • 113

upvoted 9 papers about 1 month ago

Qwen-Image-2.0-RL Technical Report

Paper • 2606.27608 • Published Jun 25 • 52

Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots

Paper • 2606.28133 • Published Jun 26 • 40

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published Jan 23 • 183

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Paper • 2509.26490 • Published Sep 30, 2025 • 22

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Paper • 2606.24530 • Published Jun 23 • 65

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published Jun 25 • 57

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published Jun 25 • 81

OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning

Paper • 2606.25757 • Published Jun 24 • 1

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published Jun 23 • 153

upvoted 2 papers about 2 months ago

GrepSeek: Training Search Agents for Direct Corpus Interaction

Paper • 2605.29307 • Published May 28 • 117

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published Jun 1 • 241