Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
For decades, much software engineering research has been dedicated to devising automated solutions aimed at enhancing developer productivity and elevating software quality. The past two decades have witnessed an unparalleled surge in the development of intelligent solutions tailored for software engineering tasks. This momentum established the Artificial Intelligence for Software Engineering (AI4SE) area, which has swiftly become one of the most active and popular areas within the software engiueering field. This Future of Software Engineering (FoSE) paper navigates through several focal points. It commences with a succinct introduction and history of AI4SE. Thereafter, it underscores the core challenges inherent to AI4SE, particularly highlighting the need to realize trustworthy and synergistic AI4SE. Progressing, the paper paints a vision for the potential leaps achievable if AI4SE's key challenges are surmounted, suggesting a transition toward Software Engineering 2.0. Two strategic roadmaps are then laid out: one centered on realizing trustworthy AI4SE, and the other on fostering synergistic AI4SE. While this paper may not serve as a conclusive guide, its intent is to catalyze further progress. The ultimate aspiration is to position AI4SE as a linchpin in redefining the horizons of software engineering, propelling us toward Software Engineering 2.0.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 1×
“Software practitioners (and companies) need certain guarantees that proprietary code and data are not retained or seeped into the underlying AI4SE model that can potentially be leaked to other users of the service, c.f., [126], [127].”
BackgroundClark, H. H., & Brennan, S. E. (1991) · Perspectives on socially shared cognition. · doi:10.1037/10096-006 · Cited by 4,555
Humans and automation: Use, misuse, disuse, abuse
Parasuraman, R., & Riley, V. (1997) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/001872097778543886 · Cited by 4,554 · cited 2×
“Prior studies have highlighted the dangers of automation misuse, e.g., [79].”
BackgroundCodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.139 · Cited by 2,824
Trust in Automation: Integrating Empirical Evidence on Factors That Influence Trust
Hoff, K. A., & Bashir, M. (2015) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720814547570 · Cited by 2,817
Foundations for an Empirically Determined Scale of Trust in Automated Systems
Jian, J.-Y., Bisantz, A. M., & Drury, C. G. (2000) · International Journal of Cognitive Ergonomics · doi:10.1207/s15327566ijce0401_04 · Cited by 1,799
DECKARD: Scalable and Accurate Tree-Based Detection of Code Clones
Jiang, L., Misherghi, G., Su, Z., & Glondu, S. (2007) · 29th International Conference on Software Engineering (ICSE'07) · doi:10.1109/icse.2007.30 · Cited by 1,039
Large Language Models for Software Engineering: A Systematic Literature Review
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3695988 · Cited by 1,029
Self-citationTrusted Execution Environment: What It is, and What It is Not
Sabt, M., Achemlal, M., & Bouabdallah, A. (2015) · 2015 IEEE Trustcom/BigDataSE/ISPA · doi:10.1109/trustcom.2015.357 · Cited by 724
Research works printed but not linked: 122
- Johnson, 1977, Lint, a C program checker, Computing Science TR, 65
- 10.1007/bfb0025774 · DOI · Paper page
- 10.1007/3-540-11494-7_22 · DOI · Paper page
- 10.1145/96267.96279 · DOI · Paper page
- Bengio, 2016, Springtime for AI: The rise of deep learning
- 10.1109/MC.2009.256 · DOI
- 10.1145/1181775.1181808 · DOI
- 10.1145/1572272.1572290 · DOI
- 10.1145/1368088.1368151 · DOI · Paper page
- Binkley, 2010, Development: Information retrieval applications, 231
- 10.1109/TSE.2012.63 · DOI · Paper page
- 10.1016/0950-5849(88)90061-4 · DOI
- 10.1145/1039174.1039188 · doi:10.1145/1039174.1039188
- Harman, 2009, Search Based Software Engineering - First International Symposium, SSBSE 2009
- 10.1145/2693208.2693219 · doi:10.1145/2693208.2693219
- 10.1109/CSMR.2013.41 · DOI · Paper page
- 10.1109/ISSRE.2013.6698918 · DOI · Paper page
- 10.1109/compsac.2013.55 · DOI
- 10.1109/MSR.2013.6624040 · DOI
- 10.1109/ICPC.2015.18 · DOI
- 10.1007/s10664-018-9642-5 · DOI
- 10.1145/3412845 · DOI
- 10.1109/TSE.2019.2906315 · DOI
- 10.1109/TSE.2021.3058985 · DOI
- 10.1109/ASE.2017.8115681 · DOI
- 10.1145/3551349.3560421 · DOI
- 10.1109/QRS.2015.14 · DOI · Paper page
- 10.1109/MSR.2015.38 · DOI · Paper page
- 10.1145/3290353 · DOI · Paper page
- Hoang, 2020, CC2Vec: distributed representations of code changes, 518, 10.1145/3377811.3380361 · DOI · Paper page
- Majumder, 2018, 500+ times faster than deep learning: a case study exploring faster methods for text mining stackoverflow, 554, 10.1145/3196398.3196424 · DOI
- 10.1145/3238147.3238190 · DOI · Paper page
- 10.1145/3460319.3464819 · DOI · Paper page
- 10.1109/ASE.2019.00011 · DOI
- 10.18653/v1/n19–1423 · DOI · Paper page
- 10.1109/ICSME46990.2020.00025 · DOI · Paper page
- 2023, OpenAI, GPT-4 technical report, abs/2303.08774 · arXiv
- 10.1145/2786805.2786809 · DOI · Paper page
- 10.1145/2931037.2931051 · DOI · Paper page
- McManus, 2023, Friend or foe: Can computer coders trust ChatGPT
- Claburn, 2023, ChatGPT creates mostly insecure code, but wont tell you unless you ask
- 10.1145/3379597.3387461 · DOI
- 10.1201/9780429258985 · DOI · Paper page
- 10.1145/1101908.1101949 · DOI · Paper page
- 10.1109/TSE.2023.3279125 · DOI
- 10.1145/2001420.2001445 · DOI · Paper page
- Christakis, 2016, What developers want and need from program analysis: An empirical study, 332, 10.1145/2970276.2970347 · DOI · Paper page
- 10.1109/ICSME.2016.67 · DOI
- Csikszentmihalyi, 1990, Flow: The Psychology of Optimal Experience
- 10.2190/T543-742X-033L-9877 · DOI
- 10.1145/3439961.3439982 · DOI
- 10.1109/ICSE-SEIP.2019.00030 · DOI
- 10.1097/00043764-197005000-00027 · doi:10.1097/00043764-197005000-00027
- 10.1109/ICPC.2015.12 · DOI · Paper page
- 10.1109/TSE.2014.2362924 · DOI
- 10.1038/nrn1201 · DOI · Paper page
- 10.1037/h0020071 · DOI · Paper page
- 10.1145/3540250.3549087 · DOI
- Hu, 2018, Deep code comment generation, 200, 10.1145/3196321.3196334 · DOI · Paper page
- Karpathy, 2017, Software 2.0
- 10.1109/TSE.2007.256941 · DOI · Paper page
- 10.1145/1557019.1557083 · DOI · Paper page
- Kruppa, 2023, Google DeepMind CEO says some form of AGI possible in a few years
- Grace, 2022, 2022 expert survey on progress in AI
- 10.1518/hfes.46.1.50.30392 · doi:10.1518/hfes.46.1.50.30392 · Paper page
- 10.1016/S0020-7373(87)80013-5 · DOI · Paper page
- 10.1109/TSE.2018.2877678 · DOI · Paper page
- 10.1145/3510003.3510152 · DOI
- Wang, 2023, Practitioners expectations on code completion, CoRR, abs/2301.03846 · arXiv
- 10.1109/ICSE-SEIP58684.2023.00043 · DOI · Paper page
- 10.1145/2884781.2884812 · DOI
- 10.1109/ASE56229.2023.00023 · DOI
- 10.2139/ssrn.4361607 · DOI · Paper page
- 10.1145/3485447.3512244 · DOI
- 10.1007/s10664-018-9661-2 · DOI
- 10.1109/CSMR.2010.18 · DOI · Paper page
- 10.1109/icsme52107.2021.00044 · DOI
- Zhang, 2023, Cupid: Leveraging ChatGPT for more accurate duplicate bug report detection, arXiv preprint
- 10.1145/3635711 · DOI · Paper page
- 10.1109/ICSE48619.2023.00181 · DOI · Paper page
- 10.1145/3611643.3616244 · DOI
- Guo, 2021, Graph-CodeBERT: Pre-training code representations with data flow
- 10.1109/SANER53432.2022.00077 · DOI
- 10.1145/3597503.3608136 · DOI
- Ahmed, 2023, Improving few-shot prompts with relevant static analysis products, arXiv preprint
- 10.1109/ASE56229.2023.00031 · DOI
- Xia, 2023, Keep the conversation going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT, CoRR, abs/2304.00385 · arXiv
- 10.1145/3510003.3510129 · DOI
- 10.1145/3585386 · doi:10.1145/3585386
- 10.1109/ICSE48619.2023.00063 · DOI
- 10.1145/3524610.3527902 · DOI
- Mohammadkhani, 2023, A systematic literature review of explainable AI for software engineering, CoRR, abs/2302.06065 · arXiv
- 10.1145/2560217.2560219 · DOI · Paper page
- 10.1109/ICPC52881.2021.00046 · DOI
- 10.1145/3533767.3534398 · DOI
- 10.1109/WCRE.2013.6671293 · DOI
- 10.1145/2584654 · doi:10.1145/2584654
- 10.1145/1993498.1993551 · DOI
- 10.1145/2351676.2351718 · doi:10.1145/2351676.2351718
- 10.1109/TSE.2013.6 · DOI
- Yang, 2023, What do code models memorize? an empirical study on large language models of code, CoRR, abs/2308.09932 · arXiv
- 10.1145/3551349.3556964 · DOI · Paper page
- 10.1145/3540250.3560883 · DOI
- Metz, 2023, Lawsuit takes aim at the way A.I. is built
- 10.1109/MC.2019.2907766 · doi:10.1109/mc.2019.2907766
- 10.1109/TSE.2002.1019480 · DOI · Paper page
- 10.1145/3236024.3236026 · DOI
- 10.1109/TSE.2021.3105556 · DOI
- 10.1145/3591227 · DOI
- Jha, 2023, CodeAttack: Code-based adversarial at-tacks for pre-trained programming language models, 14892
- 10.1109/tse.2024.3361661 · DOI · Paper page
- Nguyen, 2023, Adversarial attacks on code models with discriminative graph patterns, CoRR, abs/2308.11161 · arXiv
- Schuster, 2021, You autocomplete me: Poisoning vulnerabilities in neural code completion, 1559
- 10.1109/TSE.2021.3075215 · DOI
- 10.1109/ISSRE.2015.7381836 · DOI
- 10.1007/s10664-016-9484-y · DOI
- 10.1109/ICST46399.2020.00012 · DOI
- Satir, 1991, The Satir Model: Family Therapy & Beyond
- Lindstrom, 2003, It gets worse before it gets better: Changing to XP, Cutter IT Journal, 16, 12
- 10.1109/WCRE.2012.31 · DOI · Paper page
- 10.1109/ICSE48619.2023.00055 · DOI · Paper page
- 10.1109/CVPR52729.2023.01925 · DOI
Cited by
Large Language Models for Software Engineering: A Systematic Literature Review
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3695988 · Cited by 1,029
Self-citationShi, J., Yang, Z., & Lo, D. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3708525 · Cited by 43
“In this article, we focus on the environmental aspect of LLM4SE techniques and use the term “green”; other aspects of sustainability are beyond our scope.”
Self-citationHuman-In-the-Loop Software Development Agents
Takerngsaksiri, W., Pasuksmit, J., Thongtanunam, P., Tantithamthavorn, C., Zhang, R., Jiang, F., Li, J., Cook, E., Chen, K., & Wu, M. (2024) · arXiv · doi:10.48550/arxiv.2411.12924 · Cited by 24
The Impact of Generative AI on Creativity in Software Development: A Research Agenda
Jackson, V., Vasilescu, B., Russo, D., Ralph, P., Prikladnicki, R., Izadi, M., D’Angelo, S., Inman, S., Andrade, A., & van der Hoek, A. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3708523 · Cited by 23
Toward a Theory of Causation for Interpreting Neural Code Models
Nader Palacio, D., Velasco, A., Cooper, N., Rodriguez, A., Moran, K., & Poshyvanyk, D. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3379943 · Cited by 18
Metadata
- Authors
- Lo, D.
- Venue
- 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE)
- Publisher
- IEEE
- Published
- 2023-05-14
- Pages
- 69-85
- OpenAlex
- W4392609567
- Cited by
- 40
- References
- 35
- FWCI
- 10.66
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps. https://app.cochat.ai/papers/10.1109/icse-fose59343.2023.00010
- The paper
- Lo, D. (2023). Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps. 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE). https://doi.org/10.1109/icse-fose59343.2023.00010
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.