Author name cluster

Xinyi Dai

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAMAS Conference 2026 Conference Paper

DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education

Lingyue Fu
Datong Chen
Haowei Yuan
Xinyi Dai
Qingyao Li
Weinan Zhang
Weiwen Liu
Yong Yu

In programming education, Debugging and Teaching (DT) task is a common scenario which requires generating modification suggestions from erroneous code, error messages, reference solutions, and problem descriptions. Existing approaches struggle with complex multi-source reasoning and underutilize available reference code, limiting the effectiveness of large language models (LLMs) in DT tasks. To address these challenges, we propose DebugTA, a novel LLM-based debugging and teaching agent with specialized tools for standard code retrieval, variable substitution to align reference code, and an external compiler for real-time code analysis. Guided by pedagogical and debugging principles, DebugTA decomposes complexDTtasksintostructuredLLM–toolinteractionsthatreduce reasoning complexity. By aligning reference code with erroneous code, DebugTA enables the LLM to focus on logical errors and improves suggestion accuracy. To rigorously assess the quality of modification suggestions, we introduce a student simulator-teacher interactionparadigm. Experimentalresultsonthreereal-worldcode datasets demonstrate that DebugTA consistently improves teaching effectiveness while significantly reducing computational costs.

PDF

AAAI Conference 2019 Conference Paper

Large-Scale Interactive Recommendation with Tree-Structured Policy Gradient

Haokun Chen
Xinyi Dai
Han Cai
Weinan Zhang
Xuejian Wang
Ruiming Tang
Yuzhou Zhang
Yong Yu

Reinforcement learning (RL) has recently been introduced to interactive recommender systems (IRS) because of its nature of learning from dynamic interactions and planning for longrun performance. As IRS is always with thousands of items to recommend (i. e. , thousands of actions), most existing RLbased methods, however, fail to handle such a large discrete action space problem and thus become inefficient. The existing work that tries to deal with the large discrete action space problem by utilizing the deep deterministic policy gradient framework suffers from the inconsistency between the continuous action representation (the output of the actor network) and the real discrete action. To avoid such inconsistency and achieve high efficiency and recommendation effectiveness, in this paper, we propose a Tree-structured Policy Gradient Recommendation (TPGR) framework, where a balanced hierarchical clustering tree is built over the items and picking an item is formulated as seeking a path from the root to a certain leaf of the tree. Extensive experiments on carefully-designed environments based on two real-world datasets demonstrate that our model provides superior recommendation performance and significant efficiency improvement over state-of-the-art methods.

PDF Details