English
Related papers

Related papers: BoostAPR: Boosting Automated Program Repair via Ex…

200 papers

Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains…

Software Engineering · Computer Science 2026-02-10 Qinglin Zhu , Tianyu Chen , Shuai Lu , Lei Ji , Runcong Zhao , Murong Ma , Xiangxiang Dai , Yulan He , Lin Gui , Peng cheng , Yeyun Gong

Process reward models (PRMs) have proven effective for test-time scaling of Large Language Models (LLMs) on challenging reasoning tasks. However, reward hacking issues with PRMs limit their successful application in reinforcement…

Artificial Intelligence · Computer Science 2025-10-24 Jie Cheng , Gang Xiong , Ruixi Qiao , Lijun Li , Chao Guo , Junle Wang , Yisheng Lv , Fei-Yue Wang

Providing feedback on programming assignments is a tedious task for the instructor, and even impossible in large Massive Open Online Courses with thousands of students. Previous research has suggested that program repair techniques can be…

Programming Languages · Computer Science 2018-06-21 Sumit Gulwani , Ivan Radiček , Florian Zuleger

Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workflows faces two obstacles: the lack of environments supporting…

Machine Learning · Computer Science 2026-04-08 Cheng Jiayang , Xin Liu , Zhihan Zhang , Haoyang Wen , Zixuan Zhang , Qingyu Yin , Shiyang Li , Priyanka Nigam , Bing Yin , Chao Zhang , Yangqiu Song

Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers, which rely on mathematical logic and symbolic reasoning…

Computation and Language · Computer Science 2021-10-04 Dawn Drain , Chen Wu , Alexey Svyatkovskiy , Neel Sundaresan

Agent-repair leaderboards reorder under evaluator reconfiguration, and a measurable share of the reordering is produced by methods that consult evaluator-derived signal during internal selection of candidate repairs. We document this…

Artificial Intelligence · Computer Science 2026-05-07 Yuelin Hu , Zhenbo Yu , Zhengxue Cheng , Wei Liu , Li Song

Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation…

Machine Learning · Computer Science 2026-04-03 Rui Wu , Ruixiang Tang

A typical approach developers follow to influence an LLM's behavior in an application is through careful manipulation of the prompt, such as by adding or modifying instructions. However, merely adding more instructions provides little…

Artificial Intelligence · Computer Science 2025-10-17 Ben Elder , Evelyn Duesterwald , Vinod Muthusamy

Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…

Artificial Intelligence · Computer Science 2026-05-12 Xiyin Zeng , Yuyu Sun , Haoyang Li , Shouqiang Liu , Hao Wang

Recent machine learning papers often report 1-2 percentage point improvements from a single run on a benchmark. These gains are highly sensitive to random seeds, data ordering, and implementation details, yet are rarely accompanied by…

Machine Learning · Computer Science 2025-11-26 Wenzhang Du

Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment remains challenging: existing reinforcement learning approaches rely on coarse…

Artificial Intelligence · Computer Science 2026-03-12 Pengbo Liu

How should two language models interact to produce better code than either can alone? The conventional approach -- a reasoning model plans, a code specialist implements -- seems natural but fails: on HumanEval+, plan-then-code degrades…

Software Engineering · Computer Science 2026-03-05 Jan Miller

Retrieval-augmented agents can query external evidence, yet their reliability in multi-step reasoning remains limited: noisy retrieval may derail multi-hop question answering, while outcome-only reinforcement learning provides credit…

Artificial Intelligence · Computer Science 2026-03-13 Jiangming Shu , Yuxiang Zhang , Ye Ma , Xueyuan Lin , Jitao Sang

Retrieving the correct set of files from a large codebase is a crucial step in Automated Program Repair (APR). High recall is necessary to ensure that the relevant files are included, but simply increasing the number of retrieved files…

Software Engineering · Computer Science 2026-04-14 Mahir Labib Dihan , Faria Binta Awal , Md. Ishrak Ahsan

Automatic program repair (APR) techniques have the potential to reduce manual efforts in uncovering and repairing program defects during the code review (CR) process. However, the limited accuracy and considerable time costs associated with…

Software Engineering · Computer Science 2024-01-01 Zelin Zhao , Zhaogui Xu , Jialong Zhu , Peng Di , Yuan Yao , Xiaoxing Ma

Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood…

Machine Learning · Computer Science 2026-05-19 Yunbo Long , Tejumade Afonja , Guangya Hao , Alexandra Brintrup , Mario Fritz

Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. Recently, LLM-based APR methods have shown promise in repairing real-world bugs. However,…

Software Engineering · Computer Science 2024-06-05 Fengjie Li , Jiajun Jiang , Jiajun Sun , Hongyu Zhang

Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and…

Machine Learning · Computer Science 2026-05-19 Xiao Zhu , Xinyu Zhou , Boyu Zhu , Hanxu Hu , Mingzhe Du , Haotian Zhang , Huiming Wang , Zhijiang Guo

Automated program repair (APR) has great potential to reduce the effort and time-consumption in software maintenance and becomes a hot topic in software engineering recently with many approaches being proposed. Multi-location program repair…

Software Engineering · Computer Science 2019-01-08 Shangwen Wang , Xiaoguang Mao , Nan Niu , Xin Yi , Anbang Guo

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…

Machine Learning · Computer Science 2023-05-29 Cevahir Koprulu , Ufuk Topcu