Xin Li

lixin67's activity

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

upvoted 4 papers 6 days ago

Multi-agent cooperation through in-context co-player inference

Paper • 2602.16301 • Published 12 days ago • 24

REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents

Paper • 2602.14234 • Published 15 days ago • 26

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published 13 days ago • 100

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

Paper • 2602.16855 • Published 16 days ago • 46

upvoted a collection 19 days ago

UI-Venus

Collection

12 items • Updated 18 days ago • 37

upvoted 9 papers 19 days ago

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

Paper • 2602.10560 • Published 20 days ago • 29

BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation

Paper • 2602.09849 • Published 20 days ago • 16

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Paper • 2602.10090 • Published 20 days ago • 51

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

Paper • 2602.10063 • Published 20 days ago • 72

Code2World: A GUI World Model via Renderable Code Generation

Paper • 2602.09856 • Published 20 days ago • 195

UI-Venus-1.5 Technical Report

Paper • 2602.09082 • Published 21 days ago • 154

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Paper • 2602.05400 • Published 26 days ago • 341

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published 20 days ago • 186

Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments

Paper • 2602.01244 • Published 29 days ago • 16

liked 3 datasets 22 days ago

Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b

Viewer • Updated about 1 month ago • 306k • 10k • 312

OpenDataArena/MMFineReason-SFT-123K-Qwen3-VL-235B-Thinking

Viewer • Updated 27 days ago • 123k • 1.17k • 76

opendatalab/ChartVerse-SFT-1.8M

Viewer • Updated 21 days ago • 1.88M • 5.11k • 134

upvoted 2 papers 23 days ago

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

Paper • 2602.03955 • Published 27 days ago • 8

LatentMem: Customizing Latent Memory for Multi-Agent Systems

Paper • 2602.03036 • Published 28 days ago • 14

liked a model 26 days ago

openbmb/MiniCPM-o-4_5

Any-to-Any • 9B • Updated 6 days ago • 98.6k • 893