Elamur Research⌕
☰
home / papers / 2026 / From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

Paper · 2026 · Jiajun Zhang, Zeyu Cui, Jiaxi Yang et al.

Summary

Code autocompletion tools mostly rely on Fill-in-the-Middle (FIM), which has three problems. It assumes the surrounding code is correct, so it cannot fix bugs in that code. It depends on unaligned Base models, which raises safety concerns. And its skills do not carry over well when Chat LLMs are prompted to infill. Multi-step agentic editing avoids these issues but is too slow for real-time suggestions. The authors propose Search-and-Replace Infilling (SRI), which turns completion into a single-pass micro-edit. The model first reproduces the code region it intends to change (a SEARCH block) and then writes a replacement. This lets it fill the gap and correct nearby errors in one step. The authors built SRI-200K from The Stack v2 and fine-tuned the Qwen2.5-Coder family into SRI-Coder. With only 20k training samples, the tuned Chat models outperform their own Base versions on completion. They also keep their general coding ability, which FIM-style tuning erodes, and run at latency close to plain FIM. This makes aligned Chat models a practical, safer foundation for IDE completion.

Key points

  • Prompting safety-aligned Chat models in FIM style loses up to 59.0% of completion performance relative to their Base models (shown for Qwen2.5-Coder and DeepSeek-V3 on CrossCodeEval, RepoEval and SAFIM).
  • SRI marks the cursor with a /* MIDDLE CODE TO COMPLETE */ identifier. The editable region covers that marker plus 10 lines of surrounding context. The output is a SEARCH/REPLACE block that can be converted into a standard unified diff (patch).
  • The released resources are the SRI-200K dataset, derived from The Stack v2, and the SRI-Coder models, built on Qwen2.5-Coder at sizes from 0.5B to 32B. The evaluation covers more than 20 LLMs.
  • In ablations, SRI-Coder-32B beats three natural-language FIM tuning variants on completion benchmarks, including CrossCodeEval, RepoEval, ExecRepoBench and SAFIM. Unlike those variants, it preserves scores on HumanEval+, MBPP+, BigCodeBench (Full/Hard) and LiveCodeBench.
  • The authors note two limitations: the evaluation uses only offline benchmarks with no IDE user studies, and gains are smaller for compact models such as 0.5B. They suggest knowledge distillation as a future remedy for the latter.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksInformation Systems · 1,730 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,894 works

Cite

Cite as Jiajun Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Yuheng Jing, Zeyao Ma, Tianyi Bai, Zilei Wang, Qiang Liu, Liang Wang, Binyuan Hui and Junyang Lin. 2026. From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.361

@inproceedings{zhang2026completion,
  title = {{From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning}},
  author = {Jiajun Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Yuheng Jing, Zeyao Ma, Tianyi Bai, Zilei Wang, Qiang Liu, Liang Wang, Binyuan Hui and Junyang Lin},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.361},
  url = {https://doi.org/10.18653/v1/2026.acl-long.361}
}

References

91 references, 40 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, and 1 others. 2023. Santa-Coder: Don’t reach for the stars! arXiv preprint arXiv:2301.03988.
  2. Anthropic. 2023a. Claude 2. Technical report, Anthropic. find
  3. Anthropic. 2023b. Introducing Claude. find
  4. Mohammad Bavarian, Heewoo Jun, Nikolas Tezak, John Schulman, Christine McLeavey, Jerry Tworek, and Mark Chen. 2022. Efficient training of language models to fill in the middle. arXiv preprint arXiv:2207.14255.
  5. Ruisheng Cao, Mouxiang Chen, Jiawei Chen, Zeyu Cui, Yunlong Feng, Binyuan Hui, Yuheng Jing, Kaixin Li, Mingze Li, Junyang Lin, and 1 others. 2026. Qwen3-coder-next technical report. arXiv preprint arXiv:2603.00729.
  6. Saikat Chakraborty, Yangruibo Ding, Miltiadis Allamanis, and Baishakhi Ray. 2022. Codit: Code editing with tree-based neural models. IEEE Transactions on Software Engineering, 48(4):1385–1399. find
  7. Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, and Yunxin Liu. 2025. Grail: Learning to interact with large knowledge graphs for retrieval augmented reasoning. arXiv preprint arXiv:2508.05498. — [arXiv:2508.05498](https://arxiv.org/abs/2508.05498) find
  8. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Pondé de Oliveira Pinto, Jared Kaplan, Harrison Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others.… — Evaluating Large Language Models Trained on Code
  9. Mouxiang Chen, Hao Tian, Zhongxin Liu, Xiaoxue Ren, and Jianling Sun. 2024. Jumpcoder: Go beyond autoregressive coder via online modification. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11500–11520. find
  10. Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, Wenting Zhao, Ruisheng Cao, Jiaxi Yang, Jiawei Chen, Mingze Li, Zeyao Ma, and 1 others. 2026. Swe-universe: Scale real-world verifiable environments to millions. arXiv preprint arXiv:2602.02361. — [arXiv:2602.02361](https://arxiv.org/abs/2602.02361) find
  11. Zimin Chen, Steve James Kommrusch, Michele Tufano, Louis-Noel Pouchet, Denys Poshyvanyk, and Martin Monperrus. 2021b. Sequencer: Sequence-to-sequence learning for end-to-end program repair. IEEE Transactions on Software Engineering, page 1–1. find
  12. Wen Cheng, Ke Sun, Xinyu Zhang, and Wei Wang. 2025. Security attacks on llm-based code completion tools. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23669–23677. find
  13. DeepSeek-AI and etc. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. find
  14. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  15. Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, and Lidong Bing. 2023. Multilingual jailbreak challenges in large language models. arXiv preprint arXiv:2310.06474.
  16. Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, and Shujian Huang. 2023a. A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily. arXiv preprint arXiv:2311.08268.
  17. Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Hantian Ding, Ming Tan, Nihal Jain, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang. 2023b. Crosscodeeval: A diverse and multilingual benchmark for cross-file code completion. In Advances in Neural Information Pro… find
  18. Yifeng Ding, Hantian Ding, Shiqi Wang, Qing Sun, Varun Kumar, and Zijian Wang. 2024. Horizon-length prediction: Advancing fill-in-the-middle capabilities for code generation with lookahead planning. Preprint, arXiv:2410.03103. — [arXiv:2410.03103](https://arxiv.org/abs/2410.03103) find
  19. Chengyu Fang, Heng Guo, Zheng Jiang, Chunming He, Xiu Li, and Minfeng Xu. 2026. Photon: Speedup volume understanding with efficient multimodal large language models. arXiv preprint arXiv:2603.25155. — [arXiv:2603.25155](https://arxiv.org/abs/2603.25155) find
  20. Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida I. Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen tau Yih, Luke Zettlemoyer, and Mike Lewis. 2022. Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999, abs/2204.05999. find
  21. Glaive AI. 2023. glaive-code-assistant. https://huggingface.co/datasets/glaiveai/ glaive-code-assistant. ↗
  22. Linyuan Gong, Sida Wang, Mostafa Elhoushi, and Alvin Cheung. 2024. Evaluation of llms on syntax-aware code fill-in-the-middle tasks. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. find
  23. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y Wu, YK Li, and 1 others. 2024a. Deepseek-coder: When the large language model meets programming–the rise of code intelligence. arXiv preprint arXiv:2401.14196. find
  24. Xingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin, and Bin Hu. 2024b. Cold-attack: Jailbreaking llms with stealthiness and controllability. arXiv preprint arXiv:2402.08679. — [arXiv:2402.08679](https://arxiv.org/abs/2402.08679) find
  25. Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, and Ashish Tiwari. 2023. Grace: Generation using associated code edits. Preprint, arXiv:2305.14129. — [arXiv:2305.14129](https://arxiv.org/abs/2305.14129) find
  26. Siming Huang, Tianhao Cheng, Jason Klein Liu, Jiaran Hao, Liuyihan Song, Yang Xu, J Yang, JH Liu, Chenchen Zhang, Linzheng Chai, and 1 others. 2024. Opencoder: The open cookbook for top-tier code large language models. arXiv preprint arXiv:2411.04905.
  27. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Kai Dang, and 1 others. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186. — Qwen2.5-Coder Technical Report
  28. Tingfeng Hui, Pengyu Zhu, Bowen Ping, Ling Tang, Guanting Dong, Yaqi Zhang, and Sen Su. 2025. De-cif: Improving instruction-following through meta-decomposition. arXiv preprint arXiv:2505.13990. — [arXiv:2505.13990](https://arxiv.org/abs/2505.13990) find
  29. Faria Huq, Masum Hasan, Md Mahim Anjum Haque, Sazan Mahbub, Anindya Iqbal, and Toufique Ahmed. 2022. Review4repair: Code review aided automatic program repairing. Information and Software Technology, 143:106765. find
  30. Siyuan Jiang, Jia Li, He Zong, Huanyu Liu, Hao Zhu, Shukai Hu, Erlu Li, Jiazheng Ding, Yu Han, Wei Ning, Gen Wang, Yihong Dong, Kechi Zhang, and Ge Li. 2024. aixcoder-7b: A lightweight and effective large language model for code completion. CoRR, abs/2410.13187. — [arXiv:2410.13187](https://arxiv.org/abs/2410.13187) find
  31. Zheng Jiang, Heng Guo, Chengyu Fang, Changchen Xiao, Xinyang Hu, Lifeng Sun, and Minfeng Xu. 2026. Medvr: Annotation-free medical visual reasoning via agentic reinforcement learning. In The Fourteenth International Conference on Learning Representations. find
  32. Mingsheng Jiao, Tingrui Yu, Xuan Li, Guanjie Qiu, Xiaodong Gu, and Beijun Shen. 2023. On the evaluation of neural code translation: Taxonomy and benchmark. In 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), pages 1529–1541. IEEE. find
  33. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2023. Swe-bench: Can language models resolve real-world github issues? arXiv preprint arXiv:2310.06770.
  34. Divij Handa, Advait Chirmule, Bimal G Gajera, and Chitta Baral. 2024. Jailbreaking proprietary large language models using word substitution cipher. CoRR. find
  35. Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2024. Swe-bench: Can language models resolve real-world github issues? Preprint, arXiv:2310.06770.
  36. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, and 1 others. 2023. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352.
  37. Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, and Tatsunori Hashimoto. 2024. Exploiting programmatic behavior of llms: Dual-use through standard security attacks. In 2024 IEEE Security and Privacy Workshops (SPW), pages 132–143. IEEE. find
  38. Taewoo Kim and Joo-Haeng Lee. 2020. C-3po: Cyclic-three-phase optimization for human-robot motion retargeting based on reinforcement learning. Preprint, arXiv:1909.11303. — [arXiv:1909.11303](https://arxiv.org/abs/1909.11303) find
  39. Jia Li, Ge Li, Zhuo Li, Zhi Jin, Xing Hu, Kechi Zhang, and Zhiyi Fu. 2023. \<scp\>codeeditor\</scp\> : Learning to edit source code with pre-trained models. ACM Transactions on Software Engineering and Methodology, 32(6):1–22. find
  40. Weichen Li, Albert Jan, Baishakhi Ray, Junfeng Yang, Chengzhi Mao, and Kexin Pei. 2025. Editlord: Learning code transformation rules for code editing. Preprint, arXiv:2504.15284. — [arXiv:2504.15284](https://arxiv.org/abs/2504.15284) find
  41. Yujia Li, David H. Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, Thomas Hubert, Peter Choy, Cyprien de Masson d’Autume, Igor Babuschkin, Xinyun Chen, Po-Sen Huang, Johannes Welbl, Sven Gowal, Alexey Cherepanov, and… — Competition-Level Code Generation with AlphaCode
  42. Chenyan Liu, Yufan Cai, Yun Lin, Yuhuan Huang, Yun-rui Pei, Bo Jiang, Ping Yang, Jin Song Dong, and Hong Mei. 2024. Coedpilot: Recommending code edits with learned prior edit relevance, project-wise awareness, and interactive nature. In Proceedings of the 33rd ACM SIGSOFT International Symposium on… find
  43. Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. 2023a. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. arXiv preprint arXiv:2305.01210, abs/2305.01210.
  44. Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao. 2023b. Autodan: Generating stealthy jailbreak prompts on aligned large language models. arXiv preprint arXiv:2310.04451.
  45. Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, and 1 others. 2024. Starcoder 2 and the stack v2: The next generation. arXiv preprint arXiv:2402.19173. find
  46. Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, and Jing Zhang. 2026. Sparse-rl: Breaking the memory wall in llm reinforcement learning via stable sparse rollouts. arXiv preprint arXiv:2601.10079.
  47. Xingjun Ma, Yifeng Gao, Yixu Wang, Ruofan Wang, Xin Wang, Ye Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhan Zhao, and 1 others. 2025. Safety at scale: A comprehensive survey of large model safety. arXiv preprint arXiv:2502.05206. — [arXiv:2502.05206](https://arxiv.org/abs/2502.05206) find
  48. Zeyao Ma, Jing Zhang, Xiaokang Zhang, Jiaxi Yang, Zongmeng Zhang, Jiajun Zhang, Yuheng Jing, Lei Zhang, Hao Zheng, Wenting Zhao, and 1 others. 2026. Scaling agentic verifier for competitive coding. arXiv preprint arXiv:2602.04254. — [arXiv:2602.04254](https://arxiv.org/abs/2602.04254) find
  49. Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, and Yingbo Zhou. 2023. Codegen2: Lessons for training llms on programming and natural languages. CoRR, abs/2305.02309.
  50. OpenAI. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  51. Jiayi Pan, Xingyao Wang, Graham Neubig, Navdeep Jaitly, Heng Ji, Alane Suhr, and Yizhe Zhang. 2024. Training software engineering agents and verifiers with swe-gym. arXiv preprint arXiv:2412.21139.
  52. Jingyu Peng, Maolin Wang, Nan Wang, Jiatong Li, Yuchen Li, Yuyang Ye, Wanyu Wang, Pengyue Jia, Kai Zhang, and Xiangyu Zhao. 2025. Logic jailbreak: Efficiently unlocking llm safety restrictions through formal logical expression. arXiv preprint arXiv:2505.13527.
  53. Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, and 1 others. 2023. Code Llama: Open foundation models for code. arXiv preprint arXiv:2308.12950.
  54. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, and 1 others. 2022. BLOOM: A 176B-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100. find
  55. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36:68539–68551.
  56. Noam Shazeer. 2020. Glu variants improve transformer. Preprint, arXiv:2002.05202. find
  57. Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2020. Megatron-lm: Training multi-billion parameter language models using model parallelism. Preprint, arXiv:1909.08053. find
  58. KaShun Shum, Binyuan Hui, Jiawei Chen, Lei Zhang, Jiaxi Yang, Yuzhen Huang, Junyang Lin, Junxian He, and 1 others. 2025. Swe-rm: Execution-free feedback for software engineering agents. arXiv preprint arXiv:2512.21919. — [arXiv:2512.21919](https://arxiv.org/abs/2512.21919) find
  59. Jinbo Su, Lingzhe Gao, Wei Li, Shihao Liu, Haojie Lei, Xinyi Wang, Yuanzhao Guo, Ke Wang, Daiting Shi, and Dawei Yin. 2025. Racqc: Advanced retrieval-augmented generation for chinese query correction. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 675–689. find
  60. Jinbo Su, Yuxuan Hu, Cuiping Li, Hong Chen, Jia Li, Lintao Ma, and Jing Zhang. 2026. Tablecache: Primary foreign key guided kv cache precomputation for low latency text-to-sql. arXiv preprint arXiv:2601.08743. — [arXiv:2601.08743](https://arxiv.org/abs/2601.08743) find
  61. Shannan Yan, Jingchen Ni, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, and Fengyun Rao. 2026a. Adamem: Adaptive user-centric memory for long-horizon dialogue agents. arXiv preprint arXiv:2603.16496. — [arXiv:2603.16496](https://arxiv.org/abs/2603.16496) find
  62. Yashar Talebirad and Amirhossein Nadiri. 2023. Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314.
  63. Shannan Yan, Leqi Zheng, Keyu Lv, Jingchen Ni, Hongyang Wei, Jiajun Zhang, Guangting Wang, Jing Lyu, Chun Yuan, and Fengyun Rao. 2026b. Learning cross-view object correspondence via cycle-consistent mask prediction. arXiv preprint arXiv:2602.18996. — [arXiv:2602.18996](https://arxiv.org/abs/2602.18996) find
  64. Gemini Team. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. Preprint, arXiv:2403.05530.
  65. Qwen Team. Qwen3. 5: Towards native multimodal agents, february 2026. URL https://qwen.ai/blog. ↗
  66. Qwen Team. 2025. Qwen3-coder: Agentic coding in the world. Blog post. find
  67. Qwen team and etc. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  68. Xingyao Wang, Boxuan Li, Yufan Song, Frank F Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, and 1 others. 2024a. Opendevin: An open platform for ai software developers as generalist agents. arXiv preprint arXiv:2407.16741.
  69. Xingyao Wang, Boxuan Li, Yufan Song, Frank F Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, and 1 others. 2024b. Openhands: An open platform for ai software developers as generalist agents. arXiv preprint arXiv:2407.16741.
  70. Yuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux, Lingming Zhang, Daniel Fried, Gabriel Synnaeve, Rishabh Singh, and Sida I. Wang. 2025. Swe-rl: Advancing llm reasoning via reinforcement learning on open software evolution. Preprint, arXiv:2502.18449.
  71. Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang. 2023a. Magicoder: Source code is all you need. arXiv preprint arXiv:2312.02120, abs/2312.02120. find
  72. Zeming Wei, Yifei Wang, Ang Li, Yichuan Mo, and Yisen Wang. 2023b. Jailbreak and guard aligned language models with only few in-context demonstrations. arXiv preprint arXiv:2310.06387.
  73. Di Wu, Wasi Uddin Ahmad, Dejiao Zhang, Murali Krishna Ramanathan, and Xiaofei Ma. 2024. Repoformer: Selective retrieval for repository-level code completion. arXiv preprint arXiv:2403.10059. — [arXiv:2403.10059](https://arxiv.org/abs/2403.10059) find
  74. Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, and Lingming Zhang. 2024. Agentless: Demystifying llm-based software engineering agents. Preprint, arXiv:2407.01489.
  75. Yuan Xin, Dingfan Chen, Linyi Yang, Michael Backes, and Xiao Zhang. 2025. Jailbreaking attacks vs. content safety filters: How far are we in the llm safety arms race? arXiv preprint arXiv:2512.24044.
  76. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  77. Jian Yang, Jiajun Zhang, Jiaxi Yang, Ke Jin, Lei Zhang, Qiyao Peng, Ken Deng, Yibo Miao, Tianyu Liu, Zeyu Cui, Binyuan Hui, and Junyang Lin. 2024a. Execrepobench: Multi-level executable code completion evaluation. Preprint, arXiv:2412.11990. — [arXiv:2412.11990](https://arxiv.org/abs/2412.11990) find
  78. John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024b. Swe-agent: Agent-computer interfaces enable automated software engineering. arXiv preprint arXiv:2405.15793.
  79. Yang Yao, Xuan Tong, Ruofan Wang, Yixu Wang, Lu-jundong Li, Liang Liu, Yan Teng, and Yingchun Wang. 2025. A mousetrap: Fooling large reasoning models for jailbreak with chain of iterative chaos. arXiv preprint arXiv:2502.15806. find
  80. Sibo Yi, Yule Liu, Zhen Sun, Tianshuo Cong, Xinlei He, Jiaxing Song, Ke Xu, and Qi Li. 2024. Jailbreak attacks and defenses against large language models: A survey. arXiv preprint arXiv:2407.04295.
  81. Zheng-Xin Yong, Cristina Menghini, and Stephen H Bach. 2023. Low-resource languages jailbreak gpt-4. arXiv preprint arXiv:2310.02446.
  82. Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. 2023. Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher. arXiv preprint arXiv:2308.06463.
  83. Yi Zeng, Hongpeng Lin, Jingwen Zhang, Diyi Yang, Ruoxi Jia, and Weiyan Shi. 2024. How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lon…
  84. Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Preprint, arXiv:1910.07467. find
  85. Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou, and Weizhu Chen. 2023. Repocoder: Repository-level code completion through iterative retrieval and generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMN…
  86. Lei Zhang, Mouxiang Chen, Ruisheng Cao, Jiawei Chen, Fan Zhou, Yiheng Xu, Jiaxi Yang, Zeyao Ma, Liang Chen, Changwei Luo, and 1 others. 2026a. Megaflow: Large-scale distributed orchestration system for the agentic era. arXiv preprint arXiv:2601.07526. — [arXiv:2601.07526](https://arxiv.org/abs/2601.07526) find
  87. Lei Zhang, Jiaxi Yang, Min Yang, Jian Yang, Mouxiang Chen, Jiajun Zhang, Zeyu Cui, Binyuan Hui, and Junyang Lin. 2025. Swe-flow: Synthesizing software engineering data in a test-driven manner. Preprint, arXiv:2506.09003. — [arXiv:2506.09003](https://arxiv.org/abs/2506.09003) find
  88. Qianchi Zhang, Hainan Zhang, Liang Pang, Yongxin Tong, Hongwei Zheng, and Zhiming Zheng. 2026b. Less is more: Compact clue selection for efficient retrieval-augmented generation reasoning. In Proceedings of the ACM Web Conference 2026, pages 1971–1982. find
  89. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2026c. Stable-rag: Mitigating retrieval-permutation-induced hallucinations in retrieval-augmented generation. arXiv preprint arXiv:2601.02993.
  90. Heri Zhao, Jeffrey Hui, Joshua Howland, Nam Nguyen, Siqi Zuo, Andrea Hu, Christopher A. Choquette-Choo, Jingyue Shen, Joe Kelley, Kshitij Bansal, Luke Vilnis, Mateo Wirth, Paul Michel, Peter Choy, Pratik Joshi, Ravin Kumar, Sarmad Hashmi, Shubham Agrawal, Zhitao Gong, and 7 others. 2024. Codegemma:…
  91. Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson. 2024. Universal and transferable adversarial attacks on aligned language models, 2023. URL https://arxiv.org/abs/2307.15043, 19. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-completion-editing-unlocking-context-aware/