MapCoder: Multi-Agent Code Generation for Competitive Problem Solving
Open accessAbstract
Code synthesis, which requires a deep understanding of complex natural language (NL) problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests, presents a significant challenge.Thus, while large language models (LLMs) demonstrate impressive proficiency in natural language processing (NLP), their performance in code generation tasks remains limited.In this paper, we introduce a new approach to code generation tasks leveraging the multi-agent prompting that uniquely replicates the full cycle of program synthesis as observed in human developers.Our framework, MapCoder, consists of four LLM agents specifically designed to emulate the stages of this cycle: recalling relevant examples, planning, code generation, and debugging.After conducting thorough experiments, with multiple LLMs ablations and analyses across eight challenging competitive problem-solving and program synthesis benchmarks-MapCoder showcases remarkable code generation capabilities, achieving their new state-of-the-art (pass@1) results-(HumanEval 93.9%, MBPP 83.1%, APPS 22.0%, CodeContests 28.5%, and xCodeEval 45.3%).Moreover, our method consistently delivers superior performance across various programming languages and varying problem difficulties.
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?
Planning methods organize long-horizon software tasks through decomposition, structural grounding, trajectory search, or workflow orchestration.
“We therefore review planning methods that organize long-horizon software tasks through decomposition, structural grounding, trajectory search, or workflow orchestration [40, 41, 42, 43, 44]”
From Code as Agent Harness (2026) · cites this paper as [44]
In both personalization and specialization, interaction contexts expand far beyond what can be accommodated by prompt-based mechanisms alone.
“In both dimensions, the interaction contexts of a specific user's long-term history or the vertical tasks like coding (Islam et al., 2024) and web search (He et al., 2024a) expand far beyond what can be accommodated by prompt-based mechanisms alone.”
From A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents (2026) · cites this paper as Islam et al., 2024
Soft coordination in multi-agent frameworks can be brittle under adversarial prompts, hallucinated critiques, or multi-turn confirmation bias.
“Such soft coordination can be brittle under adversarial prompts, hallucinated critiques, or multi-turn confirmation bias.”
From SafeCodeRL: Security-Constrained Multi-Agent Reinforcement Learning for Trustworthy LLM-Generated IoT/CPS Software (2026) · cites this paper as [29]
Cites
Still being checked.
Cited by
Sorted by citations
A Survey on the Memory Mechanism of Large Language Model-based Agents
Zhang, Z., Dai, Q., Bo, X., Ma, C., Li, R., Chen, X., Zhu, J., Dong, Z., & Wen, J.-R. (2025) · ACM Transactions on Information Systems · doi:10.1145/3748302 · Cited by 118 · see citing works
Codepori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology
Rasheed, Z., Malik, S., Kemell, K.-K., Muhammad, W., Saari, M., Systä, K., & Abrahamsson, P. (2024) · doi:10.2139/ssrn.4979510 · Cited by 27 · see citing works
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 26 · see citing works
Liu, Z., Zeng, R., Wang, D., Peng, G., Liu, X., Liu, Q., Liu, P., Wang, W., & Wang, J. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3667895 · Cited by 20 · see citing works
Automatic High-Level Test Case Generation using Large Language Models
Hasan, N. B., Islam, M. A., Khan, J. Y., Senjik, S., & Iqbal, A. (2025) · International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr66628.2025.00105 · Cited by 21 · see citing works
Self-citationRGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance
Jin, H., Sun, Z., & Chen, H. (2024) · IEEE International Conference on Agents (ICA) · doi:10.1109/ica63002.2024.00037 · Cited by 15 · see citing works
Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation
Ye, S.-X., Sun, Z., Wang, G.-Q., Guo, L.-W., Liang, Q.-L., Li, Z., & Liu, Y. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3589634 · Cited by 19 · see citing works
AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers
Yang, D., Wu, A., Zhang, T., Zhang, L., Lian, X.-L., Liu, F., Ren, Y., Tian, J., & Che, X.-Y. (2024) · International Conference on Automated Software Engineering · doi:10.1109/ase63991.2025.00297 · Cited by 11 · see citing works
Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
HAAG, A. L., Fuchs, B., Kacan, A., & Lohse, O. (2025) · International Workshop on Large Language Models for Code (LLM4Code) · doi:10.1109/llm4code66737.2025.00013 · Cited by 8 · 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
Enhanced Prompting Framework for Code Summarization with Large Language Models
Fang, M., Yuan, X., Li, Y., Li, H., Fang, C., & Du, J. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3728949 · Cited by 6 · see citing works
Ashrafi, N., Bouktif, S., & Mediani, M. (2025) · Advanced Industrial Conference on Telecommunications · doi:10.1109/aict67988.2025.11268754
AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation
Zhu, Y.-H., Liu, C., He, X., Ren, X.-X., Liu, Z.-X., Pan, R.-W., & Zhang, H.-Y. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3642621 · Cited by 14 · see citing works
Measuring and mitigating debugging effectiveness decay in code language models
Adnan, M., & Kuhn, C. C. N. (2025) · Scientific Reports · doi:10.1038/s41598-025-27846-5 · Cited by 5 · see citing works
Understanding the Characteristics of LLM-Generated Property-Based Tests in Exploring Edge Cases
Tanaka, H., Tanaka, H., Shimari, K., & Matsumoto, K. (2025) · 2025 2nd IEEE/ACM International Conference on AI-powered Software (AIware) · doi:10.1109/aiware69974.2025.00009 · Cited by 2 · see citing works
Wang, Z., Chen, J., Wei, Z., Lin, L., & Tong, G. (2026) · Sensors · doi:10.3390/s26113502 · Cited by 2 · see citing works
Locally-deployed Open-source LLMs for Code Generation: Promises and Challenges
Kechaoui, T., Ouhab, M. W., Djamaa, B., & Senouci, M. R. (2025) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais66004.2025.11126523 · Cited by 2 · see citing works
ApexCodium: a Multi-Agent System for Code Generation with Enhanced Self-Reflection
Arya, M. S., Ranjan, A., & Lohia, A. A. (2025) · International Conference on Artificial Intelligence and Emerging Technologies (ICAIET) · doi:10.1109/icaiet65052.2025.11211133 · Cited by 2 · see citing works
Ibrahimzada, A. R., Paulsen, B., Kroening, D., & Jabbarvand, R. (2026) · Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3832783.3837486 · Cited by 7 · see citing works
Automated Codebase Reconciliation using Large Language Models
Gandhi, A., De, S., Chećhik, M., Pandit, V., Kiehn, M., Chee, M. C., & Bedasso, Y. (2025) · IEEE/ACM International Conference on AI Foundation Models and Software Engineering (FORGE) · doi:10.1109/forge66646.2025.00011 · Cited by 2 · see citing works
The Application of a Multimodal Analysis System Based on the COZE AI Agent in Education
Sun, Q., Zhang, Q., Yang, H., Li, B., & Wu, Y. (2025) · International Conference on Computer Science and Technologies in Education (CSTE) · doi:10.1109/cste64638.2025.11092055 · Cited by 2 · see citing works
LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review ⋆Preprint
Rasheed, Z., Muhammad, W., Kemell, K., Saari, M., & Abrahamsson, P. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6332149 · Cited by 2 · see citing works
Memory Injection Attacks on LLM Agents via Query-Only Interaction
Dong, S., Xu, S., He, P., Li, Y., Tang, J., Liu, T., Liu, H., & Xiang, Z. (2025) · arXiv · doi:10.48550/arxiv.2503.03704 · Cited by 1 · see citing works
EvoAgentX: An Automated Framework for Evolving Agentic Workflows
Wang, Y., Liu, S., Fang, J., & Meng, Z. (2025) · Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2025.emnlp-demos.47 · Cited by 1 · see citing works
Mao, K., Hu, B., Lin, R., Li, Z., Lu, G., & Zhang, Z. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1660912 · Cited by 4 · see citing works
Faultseeker: LLM-Empowered Framework for Blockchain Transaction Fault Localization
Sun, K., Xu, Z., Li, K., Zhang, L., Sun, Y., Tan, L., & Liu, Y. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00017 · Cited by 1 · see citing works
Zhang, Y., Xia, W., Zhao, B., Yuan, T., & Yu, X. (2026) · Symmetry · doi:10.3390/sym18020248 · Cited by 2 · see citing works
Hu, H., Wang, L., & Xu, X. (2025) · International Conference on Educational Technology (ICET) · doi:10.1109/icet67421.2025.11380763 · Cited by 1 · see citing works
Mitigating Cognitive Vulnerabilities in Code Generation via Multi-Agent Adversarial Debate
Liu, S., Guo, Q., Liu, X., & Liu, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792557 · Cited by 1 · see citing works
Shen, M.-T., & Joung, Y.-J. (2026) · International Workshop on Agentic Engineering · doi:10.1145/3786167.3788424 · Cited by 1 · see citing works
Lu, B., Yu, W., Wang, H., Zhao, J., Zhang, Y., & Chen, R. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner67736.2026.00022 · Cited by 1 · see citing works
Zhang, X., & Yang, B. (2026) · IEEE Access · doi:10.1109/access.2026.3722027 · Cited by 1 · see citing works
Code–Test Co-translation: Towards Practical and Effective Program Migration in the Wild
Li, X., Xie, X., Wu, J., Liu, T., & Wang, H. (2026) · Proceedings of the ACM on Programming Languages · doi:10.1145/3839490 · Cited by 1 · see citing works
Wu, C., Jiang, S., Zuo, Z., & Li, J. (2026) · Applied Sciences · doi:10.3390/app16168291 · Cited by 1 · see citing works
Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
Qiu, E. S., & Gill, J. (2026) · arXiv · doi:10.48550/arxiv.2608.18167
Li, Z., Li, Z., Guo, Z., Ren, X., & Huang, C. (2025) · arXiv · doi:10.48550/arxiv.2512.07921
Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving
Sharif, M. T., & Rehman, A. (2026) · arXiv · doi:10.48550/arxiv.2606.05704
Ning, X., Tieu, K., Fu, D., Wei, T., Li, Z., Bei, Y., Zou, J., Ai, M., Liu, Z., Li, T.-W., et al. (2026) · arXiv · doi:10.48550/arxiv.2605.18747
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052
Algorithmic Inversion: A Learnable Algorithm Representation for Code Generation
Shi, Z., Wu, F., Zeng, W., Kong, Y., Shen, S., & Wu, Y. (2025) · IEEE International Conference on Program Comprehension (ICPC) · doi:10.1109/icpc66645.2025.00054
Guo, F., Wang, Z., & Sun, J. (2025) · International Conference on Computer Science and Technologies in Education (CSTE) · doi:10.1109/cste64638.2025.11092148
Deciding the Path: Leveraging Multi-Agent Systems for Solving Complex Tasks
Abbasnejad, I., Liu, X., & Roy, A. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00405
Automating fuzz driver generation for deep learning libraries with large language models
Zheng, T., Meng, F., Yi, P., & Wu, Y. (2026) · Cybersecurity · doi:10.1186/s42400-025-00532-9
Chen, L., Deng, J., & Ren, F. (2025) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip68645.2025.11352645
MATCH: Multi-Agentic Evidence Grounding for Explainable Hate Video Detection
Li, K., Hong, R., Lang, J., Wu, J., Zhou, F., & Song, J. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3672052
A program-centered approach to solving AI tasks with ready-to-use models
Pham, T.-T., Duong, M.-Q., Luong, D.-Q., Nguyen, T.-H., Nguyen, T.-T., Nguyen, S., & Vo, H. D. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108510
Dynamic Collaboration Multi-agent Reinforcement Learning Algorithm for Power Grid Think Tank Reports
Gao, X., Sun, Z., Liu, S., Yin, W., & Yuan, J. (2026) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice68970.2026.11465688
Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development
Bowers, B., Khapre, S., & Kalita, J. K. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00174 · Cited by 4 · see citing works
TDPGen: Optimizing Agentic Code Generation via Test-Driven Planning and Hierarchical ReAct
Li, M., Yuan, S., & Han, M. (2026) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait69154.2026.11477183
VGHTCoder: Multi-agent Code Generation with Hypothesis Testing and Verification Guidance
Yin, B., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7078-2_50
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
Special Day—A Design Blueprint for Scalable Multi-Agent Architectures in Complex EDA Workflows
Tenace, V., & Gaillardon, P. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539468
Giagnorio, A., Martin-Lopez, A., & Bavota, G. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3703553
DCR-Code: A Difficulty-Aware Multi-Agent Framework for Code Generation Via Decompose-Compose-Refine
Liu, H. (2026) · International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) · doi:10.1109/aiita69518.2026.11567118
Zhu, H., Wu, J., Ling, X., Luo, T., & Zhao, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2856-0_32
Multi-Agent LLM Pipeline for Code Writing: An Experimental Study of Writer-Reviewer Architecture
Ekiz, T. K., & Konyar, M. Z. (2026) · ADBA computer science. · doi:10.69882/adba.cs.2026071
Sun, J.-W., Guo, F.-C., Yang, Z., Shen, X.-X., Chen, D.-F., Wei, M.-Q., & Wang, A.-D. (2026) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2026.3720406
BiVCoder: A Multi-Agent Framework for Code Generation via Bidirectional Code-Test Diagnosis
Li, X.-Y., Dong, J.-H., Shi, W.-H., Lu, W., & Du, X. (2026) · Knowledge Discovery and Data Mining · doi:10.1145/3770855.3818107
Cross-Model Collaboration for Enhancing LLM-Based Code Generation
Huang, J., Ye, W., Sun, W., Feng, Y., & Liu, Y. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3840382
TensorAgent: Multi-agent Framework for Automated Tensor Core Code Generation
Liu, B., Zheng, Z., & Zhang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-4805-6_16
Towards Component-Based Development for the Era of AI Coding Agents
Bureš, T., Plášil, F., Hnětynka, P., & Töpfer, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36590-3_20
Bao, T., Nayeem, M. T., Zhao, Y., Rafiei, D., & Zhang, C. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117011
KGMACG: Knowledge-Guided Multi-Agent Orchestration for Scalable Application-Level Code Generation
Yang, B., Zhang, X., Sun, W., Ma, G., Liu, H., Yang, X., Xiong, Q., Zhang, Y., Li, T., Liu, Y., et al. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3842390
RegoMender: A Multi-agent Framework for Automated Rego Policy Repair
Zhang, R., Yin, H., Hu, L., Kong, F., Liang, H., Cheng, S., Zhang, K., & Tu, B. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837490
Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration
Tang, B., Wang, T., Zhang, M., Yu, X., Chen, J., Li, B., & Zhang, K. (2026) · doi:10.1109/cvprf71909.2026.00785
AlphaCu: A Transformation-Driven Synthesis Framework for LLM-Based GPU Kernel Generation
Zhou, Y., Ma, X., Liu, Z., Wang, Q., Cui, W., Sun, W., Wang, H., Qi, B., Leng, J., Lin, Y., et al. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837433
SecChain: Operationalizing Security Guidelines for Multi-agent Smart Contract Generation
Sun, D., Nie, L., & Liu, Y. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837480
Situation Awareness in AI-Generated Industrial Cyber-Physical Systems
Bureš, T., Hnětynka, P., & Plášil, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-40108-3_7
iBRAHIMOĞLU, N., & Demi̇rezen, M. U. (2026) · Automated Software Engineering · doi:10.1007/s10515-026-00695-w
Wang, Y., Han, Y., Gao, J., Zhang, W., Wang, J., & Zhang, W. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728474
Plan4PLC: Semantic Planning for Verifiable and High-Quality PLC Code Generation
Zhou, Y., Gu, Y., Wang, T., 程良伦, & Chen, C. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729622
- Authors
- Islam, M. A., Ali, M. E., & Parvez, M. R.
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 4912-4944
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402671883
- Cited by
- 63
- References
- 0
- Citations by year
- 2026: 39 · 2025: 22 · 2024: 2
- FWCI
- 23.94
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- code generation, large language models, program synthesis, competitive programming, debugging, unit test generation
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
