paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Automated Feedback Generation for Competition-Level Code

面向竞赛级代码的自动反馈生成
ASE Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering2022匹配度 3/10 · 该论文聚焦竞赛编程错误提交的自动反馈生成，属于编程教育与调试/修复工具，与用户核心关注的静态分析、形式化验证、浮点/贝叶斯程序分析及其与 LLM/Agent 的交叉方向仅有非常间接的关联；摘要未体现 LLM/Agent、静态分析或相关理论方法。引用 19 inbox
Jialu Zhang, De Li, John Charles Kolesar, Hanyuan Shi, Ruzica Piskac
编程环境与开发者工具测试、调试与修复
crossref: 2026-09-12

AI 速览

一句话：关注竞赛编程错误提交仅获首个失败用例、反馈不足的问题，研究自动反馈生成。

竞赛编程已成为程序员检验技能的重要方式，但竞赛级题目难度高，参与者常无法一次通过。部分在线平台允许练习并提供反馈，然而对于错误提交，标准反馈仅指出第一个失败的测试用例。该信息往往不足以帮助程序员定位和修正代码中的错误，导致他们在多次尝试失败后放弃题目。标题表明论文研究面向竞赛级代码的自动反馈生成，但给出的摘要仅阐述上述问题动机，未说明具体方法、系统实现或评估结果。

问题
竞赛级编程练习的反馈不足：平台只返回第一个失败测试用例，难以帮助参赛者定位错误，导致放弃。
方法
标题指向自动反馈生成，但摘要未描述所采用的具体方法或技术。
评估
摘要未给出评估方式、实验设置或结果。
原文摘要（Abstract）

Competitive programming has become a popular way for programmers to test their skills. Competition-level programming problems are challenging in nature, and participants often fail to solve the problem on their first attempt. Some online platforms for competitive programming allow programmers to practice on competition-level problems, and the standard feedback for an incorrect practice submission is the first test case that the submission fails. Often, the failed test case does not provide programmers with enough information to resolve the errors in their code, and they abandon the problem after making several more unsuccessful attempts.

链接与引用

DOI 原文 · PDF（开放获取） ·

BibTeX 
@inproceedings{paperbot7341,
  title = {Automated Feedback Generation for Competition-Level Code},
  author = {Jialu Zhang and De Li and John Charles Kolesar and Hanyuan Shi and Ruzica Piskac},
  booktitle = {ASE},
  year = {2022},
  doi = {10.1145/3551349.3560425}
}