English
Related papers

Related papers: Agentic Rubrics as Contextual Verifiers for SWE Ag…

200 papers

Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on popular repositories…

Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These…

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy,…

Computation and Language · Computer Science 2026-02-05 Zeyao Ma , Jing Zhang , Xiaokang Zhang , Jiaxi Yang , Zongmeng Zhang , Jiajun Zhang , Yuheng Jing , Lei Zhang , Hao Zheng , Wenting Zhao , Junyang Lin , Binyuan Hui

Spec-driven development (SDD) with AI coding agents provides a structured workflow, but agents often remain "context blind" in large, evolving repositories, leading to hallucinated APIs and architectural violations. We present Spec Kit…

Software Engineering · Computer Science 2026-04-08 Pardis Taghavi , Santosh Bhavani

Large language models are increasingly used as coding agents for software engineering tasks. Current benchmarks mainly evaluate whether the agent can correctly solve the request or fix the bugs. They largely treat tasks as independent and…

Software Engineering · Computer Science 2026-05-07 Jiayuan Zhu , Junde Wu , Minhao Hu , Shengda Zhu , Jiazhen Pan , Weixiang Shen , Yijun Yang , Fenglin Liu , Jianye Hao , Yueming Jin , Qirong Ho , Min Xu

Resolving real-world software engineering (SWE) issues with autonomous agents requires complex, long-horizon reasoning. Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally…

Software Engineering · Computer Science 2026-04-17 Hao Han , Jin Xie , Xuehao Ma , Weiquan Zhu , Ziyao Zhang , ZhiLiang Long , Hongkai Chen , Qingwen Ye

Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this…

Machine Learning · Computer Science 2026-03-26 Bjarni Haukur Bjarnason , André Silva , Martin Monperrus

Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context…

Software Engineering · Computer Science 2026-05-27 Kang He , Kaushik Roy

Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2) optimal scaling of test-time compute. We introduce…

Software Engineering · Computer Science 2025-04-11 Naman Jain , Jaskirat Singh , Manish Shetty , Liang Zheng , Koushik Sen , Ion Stoica

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We…

Software Engineering · Computer Science 2026-03-17 Tingxu Han , Yi Zhang , Wei Song , Chunrong Fang , Zhenyu Chen , Youcheng Sun , Lijie Hu

Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small…

Machine Learning · Computer Science 2026-03-10 Karan Gupta , Pranav Vajreshwari , Yash Pandya , Raghav Magazine , Akshay Nambi , Ahmed Awadallah

Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that…

Software Engineering · Computer Science 2026-03-05 Shubham Ugare , Satish Chandra

While large language model agents have advanced software engineering tasks, the unscalable nature of existing test-based supervision is limiting the potential improvement of data scaling. The reason is twofold: (1) building and running test…

Computation and Language · Computer Science 2025-10-28 Junjielong Xu , Boyin Tan , Xiaoyuan Liu , Chao Peng , Pengfei Gao , Pinjia He

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current…

Software Engineering · Computer Science 2026-02-12 Qixing Zhou , Jiacheng Zhang , Haiyang Wang , Rui Hao , Jiahe Wang , Minghao Han , Yuxue Yang , Shuzhe Wu , Feiyang Pan , Lue Fan , Dandan Tu , Zhaoxiang Zhang

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

Rapidly increasing context lengths have led to the assumption that large language models (LLMs) can directly reason over entire codebases. Concurrently, recent advances in LLMs have enabled strong performance on software engineering…

Software Engineering · Computer Science 2026-03-09 Ravi Raju , Mengmeng Ji , Shubhangi Upasani , Bo Li , Urmish Thakker

We present SWE-Gym, the first environment for training real-world software engineering (SWE) agents. SWE-Gym contains 2,438 real-world Python task instances, each comprising a codebase with an executable runtime environment, unit tests, and…

Software Engineering · Computer Science 2025-06-09 Jiayi Pan , Xingyao Wang , Graham Neubig , Navdeep Jaitly , Heng Ji , Alane Suhr , Yizhe Zhang

Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving. While the majority of existing efforts focus on enhancing policy capabilities via post-training, we propose an alternative…

Artificial Intelligence · Computer Science 2026-04-30 Yuxuan Wan , Tianqing Fang , Zaitang Li , Yintong Huo , Wenxuan Wang , Haitao Mi , Dong Yu , Michael R. Lyu

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to…

Computation and Language · Computer Science 2025-12-29 KaShun Shum , Binyuan Hui , Jiawei Chen , Lei Zhang , X. W. , Jiaxi Yang , Yuzhen Huang , Junyang Lin , Junxian He
‹ Prev 1 2 3 10 Next ›