Exp-SWE-Agent: A Memory-Enhanced Coding Agent for Sequential Issue Resolution
Open accessAbstract
We present Exp-SWE-Agent, our submission to the FSE-AIWare 2026 MemComp challenge. Exp-SWE-Agent augments the Mini-SWE-Agent framework with a lightweight persistent memory module. Through a continuous retrieve-act-distill cycle, the agent extracts structured factual and experiential knowledge from past issue-resolution trajectories and uses them as strategic hints for subsequent tasks. Evaluated on a sequential 8 × 25 subset of SWE-Bench Pro, Exp-SWE-Agent increases the issue resolution rate (Pass%) from 42.7% to 47.5% while consistently reducing the number of interaction steps. These results demonstrate that structured persistent memory effectively enhances both the accuracy and efficiency of agents in long-horizon, repository-level software engineering workflows.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval
Robertson, S., & Walker, S. (1994) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1007/978-1-4471-2099-5_24 · Cited by 1,947 · see citing works
Memory in the Age of AI Agents
Hu, Y., Liu, S., Yue, Y., Zhang, G., Liu, B., Zhu, F., Lin, J., Guo, H., Dou, S., Xi, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2512.13564 · Cited by 1 · see citing works
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language ModelsPreprint
Xu, J., Deng, K., Li, W., Yu, S., Tang, H., Huang, H., Lai, Z., Zhan, Z., Wu, Y., Zhang, C., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.05459
Flagged first, then by citations
Research works printed but not linked: 5
- Silin Chen, Shaoxin Lin, Xiaodong Gu, Yuling Shi, Heng Lian, Longfei Yun, Dong Chen, Weiguo Sun, Lin Cao, and Qianxiang Wang. 2025. Swe-exp: Experience-driven software issue resolution. arXiv preprint arXiv:2507.23361 (2025). · arXiv
- Xiang Deng, Jeff Da, Edwin Pan, Yannis Yiming He, Charles Ide, Kanak Garg, Niklas Lauffer, Andrew Park, Nitin Pasari, Chetan Rane, et al. 2025. Swe-bench pro: Can ai agents solve long-horizon software engineering tasks? arXiv preprint arXiv:2509.16941 (2025). · arXiv
- Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. In The Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=VTF8yNQM66
- Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, and Mengfei Yang. 2024. DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories. In Findings of the Association for Computational Linguistics: ACL 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 3603–3614. 10.18653/v1/2024.findings-acl.214 · DOI
- Fangwen Mu, Junjie Wang, Lin Shi, Song Wang, Shoubin Li, and Qing Wang. 2025. Experepair: Dual-memory enhanced llm-based repository-level program repair. arXiv preprint arXiv:2506.10484 (2025). · arXiv
Cited by
Still being checked.
- Authors
- Li, Y., Zeng, Z., Xie, R., Ye, W., & Zhang, S.
- Affiliations
- Peking University (CN)
- Venue
- Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering
- Publisher
- ACM
- Published
- 2026-07-05
- Pages
- 1442-1446
- OpenAlex
- W7169519198
- Semantic Scholar
- a83a4c64969c9b9ca53226789d6ce8f8ec414c99
- Cited by
- 0
- References
- 3
- FWCI
- 0.00
- Type
- conference paper
- Open access
- gold
- doi.org
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Keywords
- software engineering agents, memory-augmented agents, persistent memory, problem resolution, knowledge distillation
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
