6 citations · 6 across the 6 of their papers we have counts for
6 papers
How Benchmarks Mis-Score Computer-Use Agents
Zihan Dong, Zhiyuan Ma, Zekun Wang +5
Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A s…
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Zhanbo Hua, Yifan Yao, Weihao Xie +14
While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, executable training data remains a critical bottleneck. Existing synt…
HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation
Chengrui Huang, Junshuo Zhang, Zhiyuan Ma +7
Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation i…
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou +8
Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual r…
Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
Zhiyuan Ma, Jiayu Liu, Xianzhen Luo +3
Empowering large language models (LLMs) with effective tool utilization capabilities is crucial for enabling AI agents to solve complex problems. However, current models face two m…
Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals
Xianzhen Luo, Qingfu Zhu, Zhiming Zhang +8
Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on…