With the development of large language models (LLMs) in the field of programming, intelligent programming coaching systems have gained widespread attention. However, most research focuses on repairing the buggy code of programming learners without providing the underlying causes of the bugs. To address this gap, we introduce a novel task, namely LRP (Learner-Tailored Program Repair). We then propose a novel and effective framework, LSGEN (Learner-Tailored Solution Generator), to enhance program repair while offering the bug descriptions for the buggy code. In the first stage, we utilize a repair solution retrieval framework to construct a solution retrieval database and then employ an edit-driven code retrieval approach to retrieve valuable solutions, guiding LLMs in identifying and fixing the bugs in buggy code. In the second stage, we propose a solution-guided program repair method, which fixes the code and provides explanations under the guidance of retrieval solutions. Moreover, we propose an Iterative Retrieval Enhancement method that utilizes evaluation results of the generated code to iteratively optimize the retrieval direction and explore more suitable repair strategies, improving performance in practical programming coaching scenarios. The experimental results show that our approach outperforms a set of baselines by a large margin, validating the effectiveness of our framework for the newly proposed LPR task.
REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Engineering Center for Space Utilization of Chinese Academy of Sciences（中国科学院空间利用工程技术中心）；University of Chinese Academy of Sciences（中国科学院大学）；School of Computer Science and Engineering（计算机科学与工程学院）；Northeastern University（东北大学）；New York University（纽约大学）；School of Computing（计算机学院）；National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）；Technical University of Munich（慕尼黑技术大学）
Southwest University（西南大学）；Aarhus University（奥胡斯大学）；University of York（约克大学）；Centro de Informática, Universidade Federal de Pernambuco (UFPE)（伯南布哥联邦大学信息中心）；University of Lancaster（兰卡斯特大学）
Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Carnegie Mellon University（卡内基梅隆大学）
大语言模型（LM）虽然功能强大，但也不能避免错误，而且很难重新训练。我们的目标是让LM在部署后继续改进，而不需要再培训，使用用户的反馈。我们的方法将LM与（i）用户识别输出错误并提供如何纠正错误的一般反馈的情况的不断增长的记忆（ii）校正模型，经过训练将此一般反馈转化为特定的编辑以修复模型输出。给定一个新的、看不见的输入，我们的模型可以使用来自过去类似案例的反馈来修复可能发生的输出错误。我们使用一个现有的、固定的脚本生成模型来实例化我们的方法，该模型采用一个目标（例如，“bake a cake”），并生成一个部分有序的动作序列来实现该目标，有时包含错误。我们的记忆增强系统FBNet学习应用用户反馈来修复此类错误（最多提高30分），同时开始避免在新的、看不见的示例中出现类似的过去错误（在受控设置中最多提高7分）。这是加强已部署模型的第一步，有可能扩大其效用。我们的代码和数据可在https://github.com/allenai/interscript/上获得。
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
The Hong Kong University of Science and Technology（香港科技大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Harbin Institute of Technology, Harbin（哈尔滨工业大学）
SHERLOC: Structured Diagnostic Localization for Code Repair Agents
NVIDIA（英伟达）；Santa Clara, CA 95051, USA（美国加利福尼亚州圣克拉拉）；TU Darmstadt（达姆施塔特工业大学）；National Research Center for Applied Cybersecurity ATHENE（国家应用网络安全研究中心 ATHENE）
FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing
Graduate School of Science and Technology, University of Tsukuba（筑波大学科学技术研究生院）；Center for Artificial Intelligence Research, Tsukuba Institute for Advanced Research, University of Tsukuba（筑波大学筑波高级研究院人工智能研究中心）；Institute of Systems and Information Engineering, University of Tsukuba（筑波大学系统与信息工程研究院）
BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
State Key Laboratory of Networking and Switching Technology（网络与交换技术国家重点实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）；University of Luxembourg（卢森堡大学）
