mlsanityData to 14 Oct 2026

AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities

arXiv 2508.11126 ↗First posted 15 Aug 2025cs.SEcited by 28

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code generation, these agents decompose goals, coordinate multi-step processes, and adapt based on feedback, reshaping software development practices. This survey provides a timely review of the field, introducing a taxonomy of agent behaviors and system architectures and examining relevant techniques for planning, context management, tool integration, execution monitoring, and benchmarking datasets. We highlight challenges of this fast-moving field and discuss opportunities for building reliable, transparent, and collaborative coding agents.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 127 of its 231 references that are in the map. First posted on arXiv 15 Aug 2025.

Builds on

127 of 231 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025AlphaEvolve: A coding agent for scientific and algorithmic discovery16 Jun
  2. 2025GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents29 May
  3. 2025TRAIL: Trace Reasoning and Agentic Issue Localization13 May
  4. 2025Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks12 May
  5. 2025ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation10 Mar
  6. 2024Large Language Model-Based Agents for Software Engineering: A Survey4 Sep
  7. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
  8. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May
  9. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repair25 Mar
  10. 2024Executable Code Actions Elicit Better LLM Agents1 Feb
  11. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug
  12. 2023ChatDev: Communicative Agents for Software Development16 Jul

Other references · 115

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2020Scaling Laws for Neural Language Modelscited by 6,586
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  9. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  11. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  12. 2021Program Synthesis with Large Language Modelscited by 3,637
38 more
  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  10. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  11. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  12. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
  13. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  14. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  15. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  16. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  17. 2024A Survey on Large Language Models for Code Generationcited by 658
  18. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cachecited by 637
  19. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationcited by 591
  20. 2025Kimi K2: Open Agentic Intelligencecited by 567
  21. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 558
  22. 2024InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agentscited by 538
  23. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 527
  24. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 502
  25. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 431
  26. 2022DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalecited by 407
  27. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
  28. 2019AutoML: A Survey of the State-of-the-Artcited by 390
  29. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  30. 2022A Systematic Evaluation of Large Language Models of Codecited by 363
  31. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 358
  32. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 313
  33. 2024Agent-SafetyBench: Evaluating the Safety of LLM Agentscited by 306
  34. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 300
  35. 2023Atom: Low-bit Quantization for Efficient and Accurate LLM Servingcited by 272
  36. 2024InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Managementcited by 245
  37. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  38. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 221

50 most cited of 115 All 115 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 21.

28 papers.

Sort:

By area:

  1. 2026FeatureBench: Benchmarking Agentic Coding for Complex Feature Developmentcited by 34
  2. 2025DeepCode: Open Agentic Codingcited by 16
  3. 2025CoDA: Agentic Systems for Collaborative Data Visualizationcited by 15
  4. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic Systemcited by 15
  5. 2025Practical challenges of control monitoring in frontier AI deploymentscited by 8
  6. 2026Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHubcited by 7
  7. 2026Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomycited by 6
  8. 2026Do Coding Agents Understand Least-Privilege Authorization?cited by 6
  9. 2026Toward Architecture-Aware Evaluation Metrics for LLM Agentscited by 4
  10. 2025Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancementcited by 3
  11. 2026Scaling Small Agents Through Strategy Auctionscited by 3
  12. 2026Why Human Guidance Matters in Collaborative Vibe Codingcited by 3
16 more
  1. 2026PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agentscited by 3
  2. 2025Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Educationcited by 2
  3. 2025Socio-technical aspects of Agentic AIcited by 2
  4. 2026From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systemscited by 1
  5. 2026A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedbackcited by 1
  6. 2026Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Studycited by 1
  7. 2026Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectoriescited by 1
  8. 2026Terminal Agents: A Survey of AI Agents in Command-Line Environmentscited by 1
  9. 2026From Horizontal Layering to Vertical Integration: A Comparative Study of the AI-Driven Software Development Paradigmcited by 0
  10. 2026Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimizationcited by 0
  11. 2026AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplerscited by 0
  12. 2026AgentDSE: Reasoning-Augmented Architectural Design Space Explorationcited by 0
  13. 2026Case study: solving P-99 with LPTP and an LLMcited by 0
  14. 2026Cross-Model Cross-Language AI Coding Agent Performance: Accuracy and Speed of Parallel CLRS Algorithmscited by 0
  15. 2026OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systemscited by 0
  16. 2026Marathoner: Ultra-Long-Horizon Autonomous Intelligencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
  2. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
  3. 2026Agentic Software: How AI Agents Are Restructuring the Software Paradigm
  4. 2026LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities
  5. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generation
  6. 2026Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering
  7. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  8. 2025A Self-Improving Coding Agent