8 papers
From Solver to Tutor: Evaluating the Pedagogical Intelligence of LLMs with KMP-Bench
Weikang Shi, Houxing Ren, Junting Pan +8
Large Language Models (LLMs) show significant potential in AI mathematical tutoring, yet current evaluations often rely on simplistic metrics or narrow pedagogical scenarios, faili…
WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
Zimu Lu, Houxing Ren, Yunqiao Yang +5
Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebas…
Alignment with Fill-In-the-Middle for Enhancing Code Generation
Houxing Ren, Zimu Lu, Weikang Shi +7
The code generation capabilities of Large Language Models (LLMs) have advanced applications like tool invocation and problem-solving. However, improving performance in code-related…
Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions
Ziming Cheng, Zhiyuan Huang, Junting Pan +2
Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices. However, users often in…
Probability-Consistent Preference Optimization for Enhanced LLM Reasoning
Yunqiao Yang, Houxing Ren, Zimu Lu +6
Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models (LLMs). While current…
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
Houxing Ren, Mingjie Zhan, Zhongyuan Wu +3
Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generati…