Coding agents: A comprehensive survey of automated bug fixing systems and benchmarks
Abstract
One of the trickiest problems in software engineering is automating software issue fixes, which calls for a thorough comprehension of contextual relationships, code semantics, and dynamic debugging techniques. The development of automatic program repair (APR) is examined in this survey, which traces a path from early template and constraint-based approaches to more recent developments powered by large language models (LLMs). Three main paradigms are compared here: retrieval-augmented approaches that integrate external knowledge sources, agent-based systems that use multi-agent frameworks, and agentless systems that use simplified repair pipelines. Real-world benchmarks that mimic actual engineering workflows and repository-level difficulties, such as SWE-bench, CODEAGENT-BENCH, and CodeRAG-Bench, are used to assess these cutting-edge technologies. This study demonstrates how agentic, agentless, and retrieval-augmented systems use LLMs to achieve previously unheard-of precision and scalability by following the shift from localized, single-file solutions to solving complicated, multi-file, and repository-wide difficulties. According to our findings, while complex agent architectures have potential, straightforward test-time scaling frequently produces better outcomes, especially when paired with containerized environments that allow for parallel exploration. Additionally, the survey looks at industrial applications, emphasizing effective connections with quality assurance and D…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
As Agentic AI systems scale in number of agents and diversity of specialized roles, maintaining system reliability and interpretability becomes increasingly complex.
“As Agentic AI systems scale in both the number of agents and the diversity of specialized roles, maintaining system reliability and interpretability becomes increasingly complex [212,213].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [212]
Cites
Automatically finding patches using genetic programming
Weimer, W. R., Nguyen, T. H., Goues, C. L., & Forrest, S. (2009) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse.2009.5070536 · Cited by 768 · see citing works
A Survey on Large Language Models for Code Generation
Jiang, J., Wang, F., Shen, J., Kim, S., & Kim, S. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3747588 · Cited by 251 · see citing works
DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence
Guo, D., Zhu, Q., Yang, D., Xie, Z., Dong, K., Zhang, W., Chen, G., Bi, X., Wu, Y., Li, Y. K., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.14196 · Cited by 180 · see citing works
Zhang, K., Li, J., Li, G., Shi, X., & Jin, Z. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.737 · Cited by 138 · see citing works
Demystifying LLM-Based Software Engineering Agents
Xia, C. S., Deng, Y., Dunn, S., & Zhang, L. (2025) · Proceedings of the ACM on Software Engineering · doi:10.1145/3715754 · Cited by 87 · see citing works
CodeRAG-Bench: Can Retrieval Augment Code Generation?
Wang, Z. Z., Asai, A., Yu, X. V., Xu, F. F., Xie, Y., Neubig, G., & Fried, D. (2025) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2025.findings-naacl.176 · Cited by 34 · see citing works
Neural Program Repair with Program Dependence Analysis and Effective Filter MechanismPreprint
Zhang, Y., Li, G., Jin, Z. G., & Xing, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.09315 · Cited by 8 · see citing works
SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement
Antoniades, A., Örwall, A., Zhang, K., Xie, Y., Goyal, A., & Wang, W. (2024) · arXiv · doi:10.48550/arxiv.2410.20285 · Cited by 3 · see citing works
Improving scalability of multi-agent deep reinforcement learning with suboptimal human knowledge
Liu, D., Ren, F., Yan, J., Su, G., Gu, W., & Kato, S. (2026) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-025-09729-1 · Cited by 3 · see citing works
How Should I Build A Benchmark? Revisiting Code-Related Benchmarks For LLMs
Cao, J., Chan, Y.-K., Ling, Z., Wang, W., Li, S., Liu, M., Qiao, R., Han, Y., Wang, C., Yu, B., et al. (2025) · doi:10.13140/rg.2.2.13095.87201 · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 11 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 244 · see citing works
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186 · see citing works
Patel, K., Shah, M., Qureshi, K. M., & Qureshi, M. R. N. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11435-z · Cited by 32 · see citing works
Khadem, E. A., & Movaghar, A. (2025) · Array · doi:10.1016/j.array.2025.100547 · Cited by 10 · see citing works
Fang, J., Peng, Y., Zhang, X., Wang, Y., Yi, X., Zhang, G., Xu, Y., Wu, B., Liu, S., Li, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.07407 · Cited by 6 · see citing works
LLM-based multi-agent systems for code generation: A multi-vocal literature review
Rasheeda, Z., Waseema, M., Kemella, K.-K., Saari, M., & Abrahamsson, P. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113142
- Authors
- Puvvadi, M., Arava, S. K., Santoria, A., Chennupati, S. S. P., & Puvvadi, H. V.
- Affiliations
- Adobe Systems (United States) (US)
- Indian Institute of Technology Mandi (IN)
- Rippling Senior Software Engineer,San Jose,USA
- Shell (India) (IN)
- ORCID
- Puvvadi, Meghana
- Venue
- 2025 IEEE 14th International Conference on Communication Systems and Network Technologies (CSNT)
- Publisher
- IEEE
- Published
- 2025-03-07
- Pages
- 680-686
- OpenAlex
- W4409724980
- Cited by
- 4
- References
- 11
- Citations by year
- 2026: 1 · 2025: 3
- FWCI
- 3.13
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Communication Systems and Network Technologies (CSNT) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Keywords
- automated program repair, bug fixes, large language models, multi-agent systems, retrieval-augmented generation, SWE-bench, DevOps integration, human-AI collaboration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
