Evaluating LLMs in ROS robotic software code generation
The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Experimentation in Software Engineering
Wohlin, C., Runeson, P., Höst, M., Ohlsson, M. C., Regnell, B., & Wesslén, A. (2012) · doi:10.1007/978-3-642-29044-2 · Cited by 4,460
Robot Operating System 2: Design, architecture, and uses in the wild
Macenski, S., Foote, T., Gerkey, B., Lalancette, C., & Woodall, W. (2022) · Science Robotics · doi:10.1126/scirobotics.abm6074 · Cited by 1,585 · cited 1×
“This specific crite - rion is directly grounded in the official ROS2 Managed Nodes architecture (Macenski et al. 2022), which dictates explicit state transition interfaces for robust system orchestration.”
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
Code as Policies: Language Model Programs for Embodied Control
Liang, J., Huang, W., Xia, F., Xu, P., Hausman, K., Ichter, B., Florence, P., & Zeng, A. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10160591 · Cited by 767 · cited 1×
“Concurrently, in the robotics domain, recent studies have extensively explored LLM-driven code generation, primarily shifting towards the “Code-as-Policies” paradigm and agentic frameworks (Liang et al. 2023).”
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X
Zheng, Q., Xia, X., Zou, X., Dong, Y., Wang, S., Xue, Y., Shen, L., Wang, Z., Wang, A., Li, Y., et al. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599790 · Cited by 563 · cited 1×
“(1) General-Purpose Programming Baseline : To simulate general-purpose programming, we adopt the HumanEval-X benchmark (Zheng et al. 2023) as the baseline for evaluating the code generation capabilities of current LLMs in conventional C++ software development.”
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Li, X., Liu, Y., Chen, W., You, B., Di, Z., He, Y., Zheng, S., Choe, K. W., Sun, J., Wang, S., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.12670 · Cited by 438
Rau, G., & Shih, Y. (2021) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2021.101026 · Cited by 246
Design Automation of Cyber-Physical Systems: Challenges, Advances, and Opportunities
Seshia, S. A., Hu, S., Li, W., & Zhu, Q. (2016) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2016.2633961 · Cited by 182
Evaluating Large Language Models in Class-Level Code Generation
Du, X., Liu, M., Wang, K., Wang, H., Liu, J., Chen, Y., Feng, J., Sha, C., Peng, X., & Lou, Y. (2024) · Proceedings of the IEEE/ACM 46th International Conference on Software Engineering · doi:10.1145/3597503.3639219 · Cited by 162
Assessing the quality of GitHub copilot’s code generation
Yetistiren, B., Ozsoy, I., & Tuzun, E. (2022) · Proceedings of the 18th International Conference on Predictive Models and Data Analytics in Software Engineering · doi:10.1145/3558489.3559072 · Cited by 143
A Survey on End-User Robot Programming
Ajaykumar, G., Steele, M., & Huang, C.-M. (2021) · ACM Computing Surveys · doi:10.1145/3466819 · Cited by 136
TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks
Santu, S. K. K., & Feng, D. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.946 · Cited by 135
Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models
Wang, Z., Zhou, Z., Song, D., Huang, Y., Chen, S., Ma, L., & Zhang, T. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00180 · Cited by 120
Self-citationRijwani, T., Kumari, S., Srinivas, R., Abhishek, K., Iyer, G., Vara, H., Dubey, S., Revathi, V., & Gupta, M. (2024) · International Journal on Interactive Design and Manufacturing (IJIDeM) · doi:10.1007/s12008-024-01943-7 · Cited by 120
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Luo, Z., Xu, C., Zhao, P., Sun, Q., Geng, X., Hu, W., Tao, C., Ma, J., Lin, Q., & Jiang, D. (2023) · arXiv · doi:10.48550/arxiv.2306.08568 · Cited by 120
Robotics software engineering: a perspective from the service robotics domain
García, S., Strüber, D., Brugali, D., Berger, T., & Pelliccione, P. (2020) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3368089.3409743 · Cited by 116
Safety Guardrails for LLM-Enabled Robots
Ravichandran, Z., Robey, A., Kumar, V., Pappas, G. J., & Hassani, H. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3667488 · Cited by 94
Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data
Wei, J., Kim, S., Jung, H., & Kim, Y.-H. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637364 · Cited by 84 · cited 1×
“The system prompt enables the LLM to adopt a specific role and approach problems from a designated perspective (Wei et al. 2024 ).”
How do you architect your robots? state of the practice and guidelines for ROS-based systems
Malavolta, I., Lewis, G. A., Schmerl, B. R., Lago, P., & Garlan, D. (2020) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1145/3377813.3381358 · Cited by 72
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2310.06770 · Cited by 72
Bozhinoski, D., Di Ruscio, D., Malavolta, I., Pelliccione, P., & Crnkovic, I. (2019) · Journal of Systems and Software · doi:10.1016/j.jss.2019.02.021 · Cited by 65
Runtime Verification and Field-Based Testing for ROS-Based Robotic Systems
Caldas, R., García, J. A. P., Schiopu, M., Pelliccione, P., Rodrigues, G. N., & Berger, T. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3444697 · Cited by 55
Safety Aware Task Planning via Large Language Models in Robotics
Khan, A. A., Andrev, M., Murtaza, M. A., Aguilera, S., Zhang, R., Ding, J., Hutchinson, S., & Anwar, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246041 · Cited by 54
Addressing cybersecurity challenges in robotics: A comprehensive overview
Tanimu, J., & Abada, W. (2024) · Cyber Security and Applications · doi:10.1016/j.csa.2024.100074 · Cited by 51
HumanEval on Latest GPT Models -- 2024Preprint
Li, D., & Murr, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.14852 · Cited by 36
Luo, Y., Fan, C.-K., Dong, M., Shi, J., Mi, X., Zhao, M., Zhang, B.-W., Chi, C., Liu, J., Dai, G., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37517-9_28 · Cited by 35
Industrial Progress of Robotic Automation in Mining Applications: A Survey
Du, H., Chan, L., Tong, J., Raad, R., Naghdy, F., Guo, Q., Yu, Y., Islam, M. R., Tubbal, F., Ros, M., et al. (2025) · Mining Metallurgy & Exploration · doi:10.1007/s42461-025-01219-y · Cited by 34
Portugal, D., Rocha, R. P., & Castilho, J. P. (2024) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-024-00393-4 · Cited by 29
Yang, R., Chen, H., Zhang, J., Zhao, M., Qian, C., Wang, K., Wang, Q., Koripella, T. V., Movahedi, M., Li, M., et al. (2025) · arXiv · doi:10.48550/arxiv.2502.09560 · Cited by 29 · cited 2×
“For instance, comprehensive frameworks like EmbodiedBench (Yang et al. 2025) and RoboBench (Luo et al. 2025) have been proposed to systematically evaluate multimodal LLMs on hierarchical task planning and their capacity to act as an embodied brain.”
Self-citationZhang, T., Yu, Y., Mao, X., Wang, S., Yang, K., Lu, Y., Zhang, Z., & Zhao, Y. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00104 · Cited by 26
Self-citationDemystifying issues, causes and solutions in LLM open-source projects
Cai, Y., Liang, P., Wang, Y., Li, Z., & Shahin, M. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112452 · Cited by 17
Recommendations for Negotiated Agreements
Hansen, K., Johannsen, K. S., & Larsen, A. E. (2002) · Environment and Planning C Government and Policy · doi:10.1068/c11s · Cited by 11
Zhang, L., Ju, D., Bai, K., Ni, M., Fu, Y., Marton, Z.-C., Chen, Z., & Zhang, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.04308 · Cited by 9
LLM-Driven Corrective Robot Operation Code Generation with Static Text-Based Simulation
Wang, W., Rong, Y., Li, Y. K., Jiao, L., & Yuan, J. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696332 · Cited by 7
Getting Started with ROS2 Development: A Case Study of Software Development Challenges
Daubaris, P., Linkola, S., Kantosalo, A., & Mäkitalo, N. (2023) · IEEE/ACM International Workshop on Robotics Software Engineering (RoSE) · doi:10.1109/rose59155.2023.00011 · Cited by 5
MERA Code: A Unified Framework for Evaluating Code Generation Across TasksPreprint
Chervyakov, A., Kharitonov, A., Zadorozhny, P., Pavel, A., Levichev, R., Vorobev, D., Salikhov, D., Valeev, A., Pestova, A., Dziuba, M., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.12284 · Cited by 5
A Survey on Evaluation of Embodied AIPreprint
Hou, L., Gao, L., Wu, Y., & Chang, Y. (2026) · Preprints.org · doi:10.20944/preprints202608.2328.v1 · Cited by 4
Ro-SLM: Onboard Small Language Models for Robot Task Planning and Operation Code Generation
Wang, W., Li, Y., Jiao, L., & Yuan, J. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1720 · Cited by 4
Preliminary Study of DSL Code Generation for Robotics with LLMs
Tagliaferro, A., Lestingi, L., & Rossi, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-01486-3_22 · Cited by 3
Large Language Model Reasoning Failures
Song, P., Han, P., & Goodman, N. (2026) · arXiv · doi:10.48550/arxiv.2602.06176 · Cited by 3 · cited 1×
“As comprehensively detailed in the latest surveys (Song et al. 2026) and safety-aware frameworks (Wang et al. 2025a; Khan et al. 2025; Ravichandran et al. 2026), prevalent evaluations heavily emphasize external behavioral outcomes—such as overall task success rates, physical hallucinations, and…”
LLM-Driven Corrective Robot Operation Code Generation with Static Text-Based Simulation
Wang, W., Rong, Y., Li, Y., Jiao, L., & Yuan, J. (2025) · arXiv · doi:10.48550/arxiv.2512.02002
Research works printed but not linked: 9
- Chand R, Sharma B, Kumar SA (2025) Systematic review of mobile robots applications in smart cities with future directions. J Ind Inf Integr 45:100821
- Gaboardi dos Santos V, Khadraoui I, Farhat I, Yous H, Teffahi S, Hacid H (2026) Alrm: Agentic llm for robotic manipulation. arXiv e-prints, pages arXiv–2601
- Liang J, Huang W, Xia F, Xu P, Hausman K, Ichter B, Florence P, Zeng A (2023) Code as policies: Language model programs for embodied control. In: 2023 IEEE International conference on robotics and automation (ICRA), pages 9493–9500. IEEE · DOI · Paper page
- Quigley M, Conley K, Gerkey B, Faust J, Foote T, Leibs J, Wheeler R, Ng AY et al (2009) Ros: an open-source robot operating system. In: ICRA workshop on open source software 3:5
- Saldana J (2012) The Coding Manual for Qualitative Researchers. SAGE Publications. ISBN 9781446271421. https://books.google.com/books?id=V3tTG4jvgFkC
- Seshia SA, Hu S, Li W, Zhu Q (2017a) Design automation of cyber-physical systems: Challenges, advances, and opportunities. Trans Comp-Aided Des Integ Cir Sys 36(9):1421–1434. ISSN 0278-0070. https://doi.org/10.1109/TCAD.2016.2633961 · DOI
- Seshia SA, Hu S, Li W, Zhu Q (2017b) Design automation of cyber-physical systems: Challenges, advances, and opportunities. IEEE Trans Comput-Aided Design Integ Circ Syst 36(9):1421–1434. https://doi.org/10.1109/TCAD.2016.2633961 · DOI
- Wang Z, Zhou Z, Song D, Huang Y, Chen S, Ma L, Zhang T (2025c) Towards understanding the characteristics of code generation errors made by large language models. In: 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE), pages 2587–2599. IEEE · DOI
- Xiaodong G, Chen M, Lin Y, Yuhan H, Zhang H, Wan C, Wei Z, Yong X, Wang J (2025) On the effectiveness of large language models in domain-specific code generation. ACM Trans Softw Eng Methodol 34(3):1–22
Cited by
Still being checked.
Metadata
- Authors
- Zhao, Y., Mao, X., Zhang, T., Li, T., & Xiao, Z.
- Affiliations
- National University of Defense Technology (CN)
- Corresponding author
- Zhao, Yuxin
- Mao, Xinjun
- Zhang, Tanghaoran
- Li, Tun
- Xiao, Zhiqun
- Venue
- Empirical Software Engineering
- Published
- 2026-08-05
- Volume
- 32
- Issue
- 1
- ISSN
- 1382-3256 (ISSN-L)
- 1573-7616
- OpenAlex
- W7172486132
- Semantic Scholar
- b8f2bf082d9a4ac8b5048fa1ac29ae3c49cbb8f5
- Cited by
- 0
- References
- 40
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Empirical Software Engineering (publishedVersion)
- Funders
- National Natural Science Foundation of China (62142426)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Engineering › Control and Systems Engineering › Robotics and Automated Systems
- Keywords
- large language models, robot software, code generation, robot programming
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
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.