Awesome Code Agents

The Digital World We Are Building. The Real World We Are Acting In.

A living collection of frontier research on autonomous code agents, from the code we build to the worlds we act in.

Awesome Code Agents: the digital world we build, the real world we act in

Quick Navigation

🔥 We are actively tracking the frontier research of code agents.
🧹 The list below shows the past year; the full paper list holds the complete collection.
📚 Currently collected: 470 papers. (Last update: 2026-07-12)

🧠 Foundation Models
📊 Surveys & Empirical Studies
🧱 Code as Artifact: Building the Digital World

* 💻 General Software + 🐛 Debugging & Issue Resolution + ✏️ Code Generation & Completion + 🛠️ Environment Setup & CI/CD + 🔄 Maintenance & Evolution + 🔍 Code Review + 🔒 Security + 📖 Comprehension & Documentation + 🧪 Testing & Verification + 🏗️ Feature Development * 🧊 3D & CAD * 🌐 Web Applications * 🗄️ Databases * 🎨 Graphics & Animation * ⚙️ Systems * 🎮 Games * 🔌 Hardware

🌍 Code as Agency: Acting in the Real World

* 🔬 Research & Discovery * 🖥️ Terminals & Operating Systems * 🤖 The Physical World * 🕹️ Game Worlds * 🧭 Browsers & the Web * 🧰 Software Applications

🗺️ Research Landscape
🤝 Contributing
🌟 Star History
🙏 Acknowledgements

🧠 Foundation Models

Flagship frontier models that both write code and act through it.

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling.

_Jian Yang, Shawn Guo, Wei Zhang, Tianyu Zheng, Yaxin Du, Haau-Sing Li, Jiajun Wu, Yue Song, Yan Xing, Qingsong Cai, et al._ arXiv 2026/06.

!Model

KAT-Coder Technical Report.

_Zizheng Zhan, Ken Deng, Jinghui Wang, Xiaojiang Zhang, Huaixi Tang, Minglei Zhang, Zhiyi Lai, Haoyang Huang, Wen Xiang, Kun Wu, et al._ arXiv 2025/10.

!Model

Kimi K2: Open Agentic Intelligence.

_Kimi Team: Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, Zhuofu Chen, et al._ arXiv 2025/07.

!Model

_{… plus 1 earlier paper(s): see the full list.}

📊 Surveys & Empirical Studies

Research that studies and surveys code agents themselves.

3100 Opinions on Code Review in an AI World: Building Causal Theory from Practitioner Discourse.

_Shyam Agarwal, Courtney Miller, Christian Kästner, Bogdan Vasilescu._ arXiv 2026/07.

!Empirical Study

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier.

_Eric Jiang, Xiao Liang, Yikai Zhang, Yingjia Wan, Mengting Li, Haikang Deng, Alexander K. Taylor, Justin Baker, Rushil Raghavan, Junyi Zhang, et al._ arXiv 2026/07.

!Position Paper

How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions.

_Ningzhi Tang, Chaoran Chen, Gelei Xu, Yiyu Shi, Yu Huang, Collin McMillan, Tao Dong, Toby Jia-Jun Li._ arXiv 2026/05.

!Empirical Study

TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems.

_Minxing Wang, Xiaofei Xie, Yintong Huo._ arXiv 2026/05.

!Benchmark

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents.

_Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu, Zhengyao Jiang._ arXiv 2026/05.

!Benchmark

Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks.

_Yubin Qu, Ying Zhang, Yanjun Zhang, Gelei Deng, Yuekang Li, Leo Yu Zhang, Yi Liu._ arXiv 2026/05.

!Benchmark !Empirical Study

Code as Agent Harness.

_Xuying Ning, Katherine Tieu, Dongqi Fu, Tianxin Wei, Zihao Li, Yuanchen Bei, Jiaru Zou, Mengting Ai, Zhining Liu, Ting-Wei Li, et al._ arXiv 2026/05.

!Survey

SWE-chat: Coding Agent Interactions From Real Users in the Wild.

_Joachim Baumann, Vishakh Padmakumar, Xiang Li, John Yang, Diyi Yang, Sanmi Koyejo._ arXiv 2026/04.

!Empirical Study !Training Data

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems.

_Jiacheng Liu, Xiaohan Zhao, Xinyi Shang, Zhiqiang Shen._ arXiv 2026/04.

!Empirical Study

CodeTracer: Towards Traceable Agent States.

_Han Li, Yifan Yao, Letian Zhu, Rili Feng, Hongyi Ye, Jiaming Wang, Yancheng He, Pengyu Zou, Lehan Zhang, Xinping Lei, et al._ arXiv 2026/04.

!Benchmark

Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions.

_Ningzhi Tang, Chaoran Chen, Zihan Fang, Gelei Xu, Maria Dhakal, Yiyu Shi, Collin McMillan, Yu Huang, Toby Jia-Jun Li._ arXiv 2026/04.

!Empirical Study

How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior.

_Yinan Wu, Ze Shi Li, Kathryn Thomasset Stolee, Bowen Xu._ arXiv 2026/03.

!Empirical Study

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

_Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu._ arXiv 2026/03.

!Benchmark !Empirical Study

Fingerprinting AI Coding Agents on GitHub.

_Taher A. Ghaleb._ arXiv 2026/01.

!Empirical Study

Agent READMEs: An Empirical Study of Context Files for Agentic Coding.

_Worawalan Chatlatanagulchai, Hao Li, Yutaro Kashiwa, Brittany Reid, Kundjanasith Thonglek, Pattara Leelaprute, Arnon Rungsawang, Bundit Manaskasemsak, Bram Adams, Ahmed E. Hassan, et al._ arXiv 2025/11.

!Empirical Study

Does AI-Assisted Coding Deliver? A Difference-in-Differences Study of Cursor's Impact on Software Projects.

_Hao He, Courtney Miller, Shyam Agarwal, Christian Kästner, Bogdan Vasilescu._ arXiv 2025/11.

!Empirical Study

A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks.

_Zhuowen Yin, Cuifeng Gao, Chunsong Fan, Wenzhang Yang, Yinxing Xue, Lijun Zhang._ arXiv 2025/11.

!Empirical Study

A Survey of Vibe Coding with Large Language Models.

_Yuyao Ge, Lingrui Mei, Zenghao Duan, Tianhao Li, Yujia Zheng, Yiwei Wang, Lexin Wang, Jiayu Yao, Tianyu Liu, Yujun Cai, et al._ arXiv 2025/10.

!Survey

How can we assess human-agent interactions? Case studies in software agent design.

_Valerie Chen, Rohit Malhotra, Xingyao Wang, Juan Michelini, Xuhui Zhou, Aditya Bharat Soni, Hoang H. Tran, Calvin Smith, Ameet Talwalkar, Graham Neubig._ arXiv 2025/10.

!Empirical Study

A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System.

_Jiale Guo, Suizhi Huang, Mei Li, Dong Huang, Xingsheng Chen, Regina Zhang, Zhijiang Guo, Han Yu, Siu-Ming Yiu, Christian Jensen, et al._ arXiv 2025/10.

!Survey

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub.

_Miku Watanabe, Hao Li, Yutaro Kashiwa, Brittany Reid, Hajimu Iida, Ahmed E. Hassan._ arXiv 2025/09.

!Empirical Study

Agentic Software Engineering: Foundational Pillars and a Research Roadmap.

_Ahmed E. Hassan, Hao Li, Dayi Lin, Bram Adams, Tse-Hsun Chen, Yutaro Kashiwa, Dong Qiu._ arXiv 2025/09.

!Position Paper

"My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants.

_Yunbo Lyu, Zhou Yang, Jieke Shi, Jianming Chang, Yue Liu, David Lo._ ASE 2025.

!Empirical Study

A Survey on Code Generation with LLM-based Agents.

_Yihong Dong, Xue Jiang, Jiaru Qian, Tian Wang, Kechi Zhang, Zhi Jin, Ge Li._ arXiv 2025/07.

!Survey

The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering.

_Hao Li, Haoxiang Zhang, Ahmed E. Hassan._ arXiv 2025/07.

!Empirical Study !Training Data

Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity.

_Joel Becker, Nate Rush, Elizabeth Barnes, David Rein._ arXiv 2025/07.

!Empirical Study

_{… plus 9 earlier paper(s): see the full list.}

🧱 Code as Artifact: Building the Digital World

Agents that build software, from one function to an entire system.

💻 General Software

Writing and maintaining general-purpose software.

🐛 Debugging & Issue Resolution

Reproducing, locating, and fixing reported bugs.

AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation.

_Andrey Podivilov, Vadim Lomshakov, Sergey Savin, Matvei Startsev, Roman Pozharskiy, Maksim Parshin, Sergey Nikolenko._ arXiv 2026/07.

!Empirical Study !Benchmark

Dockerless: Environment-Free Program Verifier for Coding Agents.

_Wenhao Zeng, Yuling Shi, Xiaodong Gu, Chao Hu, Chaofan Wang, Yuhao Cui, Hongting Zhou, Mengnan Qi, Jianqiao Wangni, Zhaojian Yu, et al._ arXiv 2026/06.

!Training Data

FastContext: Training Efficient Repository Explorer for Coding Agents.

_Shaoqiu Zhang, Maoquan Wang, Yuling Shi, Yuhang Wang, Xiaodong Gu, Yongqiang Yao, Tori Gong, Sheng Chen, Rao Fu, Anisha Agarwal, et al._ arXiv 2026/06.

!Model

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks.

_Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu, Yuchuan Tian, Wei He, Hang Zhou, Jianyuan Guo, Hailin Hu, Lin Ma, et al._ arXiv 2026/06.

!Benchmark

SWE-Explore: Benchmarking How Coding Agents Explore Repositories.

_Shaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi, Wenhao Zeng, Maoquan Wang, Shilin He, Ningyuan Xu, Siyu Ye, Kai Cai, et al._ arXiv 2026/06.

!Benchmark

CODESKILL: Learning Self-Evolving Skills for Coding Agents.

_Yanzhou Li, Yiran Zhang, Xiaoyu Zhang, Xiaoxia Liu, Yang Liu._ arXiv 2026/05. Paper</a>

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation.

_Priyam Sahoo, Gaurav Mittal, Xiaomin Li, Shengjie Ma, Benjamin Steenhoek, Pingping Lin, Yu Hu._ arXiv 2026/05.

!Benchmark

TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering.

_Yuan Sui, Yulin Chen, Yibo Li, Xue Jiang, Yufei He, Yihong Dong, Xiaoxin He, Tianyu Gao, Bryan Hooi._ arXiv 2026/05. Paper</a>

Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis.

_Jiahong Xiang, Xiaoyang Xu, Xiaopan Chu, Hongliang Tian, Yuqun Zhang._ arXiv 2026/04. Paper</a>

Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks.

_Sanidhya Vijayvargiya, Vijay Viswanathan, Graham Neubig._ arXiv 2026/04.

!Model

Scaling Test-Time Compute for Agentic Coding.

_Joongwon Kim, Wannan Yang, Kelvin Niu, Hongming Zhang, Yun Zhu, Eryk Helenowski, Ruan Silva, Zhengxing Chen, Srinivasan Iyer, Manzil Zaheer, et al._ arXiv 2026/04. Paper</a>

How and Why Agents Can Identify Bug-Introducing Commits.

_Niklas Risse, Marcel Böhme._ arXiv 2026/03.

!Empirical Study

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code.

_Myeongsoo Kim, Dingmin Wang, Siwei Cui, Farima Farmahinifarahani, Terry Yue Zhuo, Shweta Garg, Baishakhi Ray, Rajdeep Mukherjee, Varun Kumar._ arXiv 2026/03.

!Empirical Study

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents.

_Jiarong Liang, Zhiheng Lyu, Zijie Liu, Xiangchao Chen, Ping Nie, Kai Zou, Wenhu Chen._ arXiv 2026/03.

!Training Data

daVinci-Env: Open SWE Environment Synthesis at Scale.

_Dayuan Fu, Shenyu Wu, Yunze Wu, Zerui Peng, Yaxing Huang, Jie Sun, Ji Zeng, Mohan Jiang, Lin Zhang, Yukun Li, et al._ arXiv 2026/03.

!Training Data !Model

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

_Guoxin Chen, Fanzhe Meng, Jiale Zhao, Minghao Li, Daixuan Cheng, Huatong Song, Jie Chen, Yuzhi Lin, Hui Chen, Xin Zhao, et al._ arXiv 2026/03.

!Benchmark

SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark.

_Boxi Yu, Yang Cao, Yuzhong Zhang, Liting Lin, Junjielong Xu, Zhiqing Zhong, Qinghua Xu, Guancheng Wang, Jialun Cao, Shing-Chi Cheung, et al._ arXiv 2026/02.

!Benchmark

SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale.

_Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Alexander Golubev._ arXiv 2026/02.

!Training Data !Benchmark

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents.

_Danlong Yuan, Wei Wu, Enhan Zhao, Zhengren Wang, Xueliang Zhao, Huishuai Zhang, Dongyan Zhao._ arXiv 2026/02. Paper</a>

Immersion in the GitHub Universe: Scaling Coding Agents to Mastery.

_Jiale Zhao, Guoxin Chen, Fanzhe Meng, Minghao Li, Jie Chen, Hui Xu, Yongshuai Sun, Wayne Xin Zhao, Ruihua Song, Yuan Zhang, et al._ arXiv 2026/02.

!Training Data

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents.

_Zhi Chen, Zhensu Sun, Yuling Shi, Chao Peng, Xiaodong Gu, David Lo, Lingxiao Jiang._ arXiv 2026/02.

!Empirical Study

SWE-Universe: Scale Real-World Verifiable Environments to Millions.

_Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, Wenting Zhao, Ruisheng Cao, Jiaxi Yang, Jiawei Chen, Mingze Li, Zeyao Ma, et al._ arXiv 2026/02.

!Training Data

Closing the Loop: Universal Repository Representation with RPG-Encoder.

_Jane Luo, Chengyu Yin, Xin Zhang, Qingtao Li, Steven Liu, Yiming Huang, Jie Wu, Hao Liu, Yangyu Huang, Yu Kang, et al._ arXiv 2026/02. Paper</a>

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving.

_Chaofan Tao, Jierun Chen, Yuxin Jiang, Kaiqi Kou, Shaowei Wang, Ruoyu Wang, Xiaohui Li, Sidi Yang, Yiming Du, Jianbo Dai, et al._ arXiv 2026/01.

!Training Data !Model

Toward Training Superintelligent Software Agents through Self-Play SWE-RL.

_Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel Synnaeve, Daniel Fried, Lingming Zhang, Sida Wang._ arXiv 2025/12.

!Training Data

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases.

_Zhaodong Wang, Zhenting Qi, Sherman Wong, Nathan Hu, Samuel Lin, Jun Ge, Erwin Gao, Wenlin Chen, Yilun Du, Minlan Yu, et al._ arXiv 2025/12. Paper</a>

InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution.

_KeFan Li, Mengfei Wang, Hengzhi Zhang, Zhichao Li, Yuan Yuan, Mu Li, Xiang Gao, Hailong Sun, Chunming Hu, Weifeng Lv._ arXiv 2025/11. Paper</a>

Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?

_Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang._ arXiv 2025/11.

SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models.

_Jingxuan Xu, Ken Deng, Weihao Li, Songwei Yu, Huaixi Tang, Haoyang Huang, Zhiyi Lai, Zizheng Zhan, Yanan Wu, Chenchen Zhang, et al._ arXiv 2025/11.

!Benchmark

The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents.

_Xingyao Wang, Simon Rosenberg, Juan Michelini, Calvin Smith, Hoang Tran, Engel Nyst, Rohit Malhotra, Xuhui Zhou, Valerie Chen, Robert Brennan, et al._ arXiv 2025/11.

SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks.

_Sanket Mhatre, Yasharth Bajpai, Sumit Gulwani, Emerson Murphy-Hill, Gustavo Soares._ arXiv 2025/11.

!Benchmark

HAFixAgent: History-Aware Automated Program Repair Agent.

_Yu Shi, Hao Li, Bram Adams, Ahmed E. Hassan._ arXiv 2025/11. Paper</a>

Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories.

_Oorja Majgaonkar, Zhiwei Fei, Xiang Li, Federica Sarro, He Ye._ arXiv 2025/10.

!Empirical Study

TDFlow: Agentic Workflows for Test Driven Software Engineering.

_Kevin Han, Siddharth Maddikayala, Tim Knappe, Om Patel, Austen Liao, Amir Barati Farimani._ arXiv 2025/10. Paper</a>

BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills.

_Atharv Sonwane, Isadora White, Hyunji Lee, Matheus Pereira, Lucas Caccia, Minseon Kim, Zhengyan Shi, Chinmay Singh, Alessandro Sordoni, Marc-Alexandre Côté, et al._ arXiv 2025/10.

!Training Data

When Old Meets New: Evaluating the Impact of Regression Tests on SWE Issue Resolution.

_Yang Chen, Toufique Ahmed, Reyhaneh Jabbarvand, Martin Hirzel._ arXiv 2025/10. Paper</a>

More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents.

_Pengfei Gao, Chao Peng._ arXiv 2025/10.

!Empirical Study

SIADAFIX: issue description response for adaptive program repair.

_Xin Cao, Nan Yu._ arXiv 2025/10.

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling.

_Xu Yang, Jiayuan Zhou, Michael Pacheco, Wenhan Zhu, Pengfei He, Shaowei Wang, Kui Liu, Ruiqi Pan._ arXiv 2025/10.

Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation.

_Spandan Garg, Ben Steenhoek, Yufan Huang._ arXiv 2025/10.

!Benchmark

REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement.

_Anvith Pabba, Simin Chen, Alex Mathai, Anindya Chakraborty, Baishakhi Ray._ arXiv 2025/10. Paper</a>

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair.

_José Cambronero, Michele Tufano, Sherry Shi, Renyao Wei, Grant Uy, Runxiang Cheng, Chin-Jung Liu, Shiying Pan, Satish Chandra, Pat Rondon._ arXiv 2025/10. Paper</a>

Improving Code Localization with Repository Memory.

_Boshi Wang, Weijian Xu, Yunsheng Li, Mei Gao, Yujia Xie, Huan Sun, Dongdong Chen._ arXiv 2025/10. Paper</a>

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

_Siru Ouyang, Jun Yan, I-Hung Hsu, Yanfei Chen, Ke Jiang, Zifeng Wang, Rujun Han, Long T. Le, Samira Daruki, Xiangru Tang, et al._ arXiv 2025/09. Paper</a>

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents.

_Zonghan Yang, Shengjie Wang, Kelin Fu, Wenyang He, Weimin Xiong, Yibo Liu, Yibo Miao, Bofei Gao, Yejie Wang, Yingwei Ma, et al._ arXiv 2025/09.

!Model !Training Data

A Benchmark for Localizing Code and Non-Code Issues in Software Projects.

_Zejun Zhang, Jian Wang, Qingyun Yang, Yifan Pan, Yi Tang, Yi Li, Zhenchang Xing, Tian Zhang, Xuandong Li, Guoan Zhang._ arXiv 2025/09.

!Benchmark

Extracting Conceptual Knowledge to Locate Software Issues.

_Ying Wang, Wenjun Mao, Chong Wang, Zhenhao Zhou, Yicheng Zhou, Wenyun Zhao, Yiling Lou, Xin Peng._ arXiv 2025/09. Paper</a>

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

_Xiang Deng, Jeff Da, Edwin Pan, Yannis Yiming He, Charles Ide, Kanak Garg, Niklas Lauffer, Andrew Park, Nitin Pasari, Chetan Rane, et al._ arXiv 2025/09.

!Benchmark

An Empirical Study on Failures in Automated Issue Solving.

_Simiao Liu, Fang Liu, Liehao Li, Xin Tan, Yinghao Zhu, Xiaoli Lian, Li Zhang._ arXiv 2025/09.

!Empirical Study

SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints.

_Zhiyu Fan, Kirill Vasilevski, Dayi Lin, Boyuan Chen, Yihao Chen, Zhiqing Zhong, Jie M. Zhang, Pinjia He, Ahmed E. Hassan._ arXiv 2025/09.

!Empirical Study

SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories.

_Junhao Wang, Daoguang Zan, Shulin Xin, Siyao Liu, Yurong Wu, Kai Shen._ arXiv 2025/09.

!Training Data

Automated Generation of Issue-Reproducing Tests by Combining LLMs and Search-Based Testing.

_Konstantinos Kitsios, Marco Castelluccio, Alberto Bacchelli._ ASE 2025.

Execution-Feedback Driven Test Generation from SWE Issues.

_Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel._ arXiv 2025/08. Paper</a>

Tool-integrated Reinforcement Learning for Repo Deep Search.

_Zexiong Ma, Chao Peng, Qunhong Zeng, Pengfei Gao, Yanzhen Zou, Bing Xie._ arXiv 2025/08.

!Training Data

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning.

_Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Sergey Abramov, Andrei Andriushchenko, Filipp Fisin, et al._ arXiv 2025/08. Paper</a>

SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents.

_Jiaye Lin, Yifu Guo, Yuzhen Han, Sen Hu, Ziyi Ni, Licheng Wang, Mingguang Chen, Hongzhang Liu, Ronghao Chen, Yangfan He, et al._ NeurIPS 2025.

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale.

_Zhilong Chen, Chengzong Zhao, Boyuan Chen, Dayi Lin, Yihao Chen, Arthur Leung, Gopi Krishnan Rajbahadur, Gustavo Oliva, Haoxiang Zhang, Aadi Bhatia, et al._ arXiv 2025/08.

!Training Data !Benchmark

Leveraging Large Language Model for Information Retrieval-based Bug Localization.

_Moumita Asad, Rafed Muhammad Yasir, Sam Malek._ arXiv 2025/08. Paper</a>

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling.

_Trae Research Team: Pengfei Gao, Zhao Tian, Xiangxin Meng, Xinchen Wang, Ruida Hu, Yuanan Xiao, Yizhou Liu, Zhao Zhang, Junjie Chen, Cuiyun Gao, et al._ arXiv 2025/07.

SWE-Exp: Experience-Driven Software Issue Resolution.

_Silin Chen, Shaoxin Lin, Xiaodong Gu, Yuling Shi, Heng Lian, Longfei Yun, Dong Chen, Weiguo Sun, Lin Cao, Qianxiang Wang._ arXiv 2025/07.

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution.

_Han Li, Yuling Shi, Shaoxin Lin, Xiaodong Gu, Heng Lian, Xin Wang, Yantao Jia, Tao Huang, Qianxiang Wang._ arXiv 2025/07.

AutoCodeSherpa: Symbolic Explanations in AI Coding Agents.

_Sungmin Kang, Haifeng Ruan, Abhik Roychoudhury._ arXiv 2025/07. Paper</a>

Prometheus: Unified Knowledge Graphs for Issue Resolution in Multilingual Codebases.

_Zimin Chen, Yue Pan, Siyu Lu, Jiayi Xu, Claire Le Goues, Martin Monperrus, He Ye._ arXiv 2025/07.

Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback.

_Chandra Maddila, Adam Tait, Claire Chang, Daniel Cheng, Nauman Ahmad, Vijayaraghavan Murali, Marshall Roch, Arnaud Avondet, Aaron Meltzer, Victor Montalvao, et al._ TSE 2025.

!Empirical Study

AssertFlip: Reproducing Bugs via Inversion of LLM-Generated Passing Tests.

_Lara Khatib, Noble Saji Mathews, Meiyappan Nagappan._ arXiv 2025/07. Paper</a>

SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks.

_Pavel Adamenko, Mikhail Ivanov, Aidar Valeev, Rodion Levichev, Pavel Zadorozhny, Ivan Lopatin, Dmitry Babayev, Alena Fenogenova, Valentin Malykh._ arXiv 2025/07.

!Benchmark

SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation.

_Gustavo A. Oliva, Gopi Krishnan Rajbahadur, Aaditya Bhatia, Haoxiang Zhang, Yihao Chen, Zhilong Chen, Arthur Leung, Dayi Lin, Boyuan Chen, Ahmed E. Hassan._ ASE 2025.

!Benchmark

_{… plus 86 earlier paper(s): see the full list.}

✏️ Code Generation & Completion

Generating and completing code, from a function to a whole repository.

ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis.

_Eagl Huang._ arXiv 2026/06. Paper</a>

**DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire

... (README truncated for length)

EuniAI/awesome-code-agents: A living collection of frontier research on code agents, from the code we build to the worlds we act in.

Awesome Code Agents

The Digital World We Are Building. The Real World We Are Acting In.

Quick Navigation

🧠 Foundation Models

📊 Surveys & Empirical Studies

🧱 Code as Artifact: Building the Digital World

💻 General Software

🐛 Debugging & Issue Resolution

✏️ Code Generation & Completion

Reading Mode

Related Stories

Dolly Parton's Imagination Library

Oregon Police Are Charging a Local News Outlet $2.5M for Records About One Cop

I refuse to accept a censored Internet. Join Me at FOSDEM 27

A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis

Sabre Wulf Remastered

Related Stories