Xiangyan Liu
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
arXiv 2026
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
arXiv 2026
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
arXiv 2026
Kimi K2.5: Visual Agentic Intelligence
arXiv 2026
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
arXiv 2025
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
arXiv 2025
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
arXiv 2025
Fostering Video Reasoning via Next-Event Prediction
arXiv 2025
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
arXiv 2024
Towards Robust Multi-Modal Reasoning via Model Selection
arXiv 2023
Affiliations
Frequent co-authors
10from 10 papers