49 citations · 77 across the 17 of their papers we have counts for
10 papers · 1 filter
TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
Shoufa Chen, Luyuan Wang, Xuan Yang +7
As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader range of general computer-use ta…
Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions
Xuan Yang, Hao Xu, Tingfeng Hui +4
Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks m…
GenClaw: Code-Driven Agentic Image Generation
Junyan Ye, Jun He, Zilong Huang +4
Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocation capabilities. Yet, existin…
Dynamic Shapley Computation
Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen +1
Shapley-based data valuation provides a principled way to quantify the contribution of training data, but its high computational cost makes it impractical in dynamic settings where…
NodeSyn: Socially Aligned Synthetic Data for AI Evaluation
Qazi Mamunur Rashid, Xuan Yang, Zhengzhe Yang +5
Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the soci…
AcademiClaw: When Students Set Challenges for AI Agents
Junjie Yu, Pengrui Lu, Weiye Si +75
Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We intro…
MPCEval: A Benchmark for Multi-Party Conversation Generation
Minxing Zhang, Yi Yang, Zhuofan Jia +5
Multi-party conversation generation, such as smart reply and collaborative assistants, is an increasingly important capability of generative AI, yet its evaluation remains a critic…
Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation
Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen +1
The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global…
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Xuan Yang, Jiayu Liu, Yuhang Lai +3
Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated…
Batch-of-Thought: Cross-Instance Learning for Enhanced LLM Reasoning
Xuan Yang, Furong Jia, Roy Xie +4
Current Large Language Model reasoning systems process queries independently, discarding valuable cross-instance signals such as shared reasoning patterns and consistency constrain…