Arrow Research search

Author name cluster

Qingyao Li

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

Possible papers

2

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

AAMAS Conference 2026 Conference Paper

Learning Semantic and Structure Aware Representation with Large Language Models for Concept Recommendation

  • Qingyao Li
  • Wei Xia
  • Kounianhua Du
  • Qiji Zhang
  • Weinan Zhang
  • Ruiming Tang
  • Yong Yu

Concept recommendation aims to suggest the next concept aligned with both the learner’s state and the educational knowledge system. However, existing methods often overlook concept semantics, leadingtorecommendationsthatlacksemanticrelevanceandstructural consistency. To address this, we propose SSRec, a novel Semantic and Structure aware representation learning framework. SSRec leverages Large Language Models (LLMs) to capture concept semanticsandintroducesagraph-basedadapter. Thisadapternotonly integrates structural relationships but also transforms anisotropic text encodings into a smooth representation space. Extensive experiments on real-world datasets demonstrate that SSRec significantly outperforms state-of-the-art baselines in delivering accurate and consistent recommendations.

PDF
v2026.09.13