Junxiao Yang

yangjunxiao2021's activity

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

upvoted a paper about 2 months ago

HaluMem: Evaluating Hallucinations in Memory Systems of Agents

Paper • 2511.03506 • Published Nov 5, 2025 • 93

upvoted 3 papers 2 months ago

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published Oct 29, 2025 • 45

DeepAgent: A General Reasoning Agent with Scalable Toolsets

Paper • 2510.21618 • Published Oct 24, 2025 • 99

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

Paper • 2509.09677 • Published Sep 11, 2025 • 34

upvoted an article 2 months ago

view article

Article

DABStep: Data Agent Benchmark for Multi-step Reasoning

• 
• 
• +4

Feb 4, 2025

•

121

upvoted a paper 2 months ago

It Takes Two: Your GRPO Is Secretly DPO

Paper • 2510.00977 • Published Oct 1, 2025 • 31

upvoted a collection 2 months ago

Agent & RL

Collection

55 items • Updated Nov 27, 2025 • 21

upvoted 2 papers 2 months ago

Glyph: Scaling Context Windows via Visual-Text Compression

Paper • 2510.17800 • Published Oct 20, 2025 • 67

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Paper • 2510.15444 • Published Oct 17, 2025 • 147

liked a dataset 3 months ago

zai-org/DeepDive

Viewer • Updated Sep 17, 2025 • 4.11k • 3.03k • 15

liked a model 3 months ago

Qwen/Qwen3-Embedding-8B

Feature Extraction • 8B • Updated Jul 7, 2025 • 969k • • 508

liked a Space 3 months ago

Running

22

BrowseComp-Plus

🥇

22

Fair and Transparent Evaluation of Deep-Research Agents

liked a dataset 3 months ago

openai/BrowseCompLongContext

Viewer • Updated Aug 9, 2025 • 295 • 773 • 44

upvoted 3 papers 3 months ago

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

Paper • 2508.07976 • Published Aug 11, 2025 • 51

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Paper • 2510.05592 • Published Oct 7, 2025 • 106

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs

Paper • 2509.24107 • Published Sep 28, 2025 • 78

liked 2 datasets 3 months ago

Tevatron/browsecomp-plus

Viewer • Updated 11 days ago • 830 • 2.53k • 21

PALIN2018/BrowseComp-ZH

Viewer • Updated May 9, 2025 • 289 • 227 • 6

upvoted 2 papers 3 months ago

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Paper • 2504.12516 • Published Apr 16, 2025 • 1

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Paper • 2504.19314 • Published Apr 27, 2025 • 7