Overview

Agentic code generation studies how language models can build software through multi-step workflows rather than producing code in a single response. Common approaches combine planning, repository or documentation retrieval, tool use, execution-based testing, and iterative debugging; multi-agent collaboration and formal verification are also used to improve complex or safety-critical work. Evaluation spans coding benchmarks such as SWE-bench and LiveCodeBench, repository-level tasks, and domain-specific tests that check whether generated systems actually run and behave as intended. A central challenge is making gains in functional correctness reliable without driving up cost or sacrificing security, maintainability, and faithful adherence to specifications.

Latest papers

CardsList

130 papers18 papers in the last four weeks, up 38% on the four weeks before. 0.1% of all new papers.

  1. HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs

    Apr 30, 2026Chang-Chih Meng, Yu-Ren Lu, Guan-Yu Lin +3Electronic Design AutomationLLM-Based Program Synthesis

  2. FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean

    Apr 24, 2026Jordan Meadows, Lan Zhang, Andre FreitasHuman-in-the-Loop AIAgentic Code Generation

  3. Agentic AI-assisted coding offers a unique opportunity to instill epistemic grounding during software development

    Apr 23, 2026Magnus Palmblad, Jared M. Ragland, Benjamin A. NeelyLLM GroundingScientific Code Generation

  4. From Clinical Intent to Clinical Model: Autonomous Coding-Agents for Clinician-driven AI Development

    Apr 18, 2026Zihao Zhao, Frederik Hauke, Juliana De Castilhos +4AI Coding AgentsAgentic Code Generation

  5. AgentGA: Evolving Code Solutions in Agent-Seed Space

    Apr 16, 2026David Y. Y. Tan, Kellie Chin, Jingxian ZhangMetaheuristic OptimizationAgentic Code Generation

  6. CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation

    Apr 15, 2026Duy Tung Doan, Quang Huy Phung, Dzung Nguyen +1Code GenerationAgentic Code Generation

  7. CodeComp: Structural KV Cache Compression for Agentic Coding

    Apr 11, 2026Qiujiang Chen, Jing Xiong, Chenyang Zhao +2KV-Cache CompressionSoftware Engineering

  8. Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm

    Apr 10, 2026Yi Lin, Lujin Zhao, Yijie ShiCode GenerationRepository-Level Code Generation

  9. Beyond Human-Readable: Rethinking Software Engineering Conventions for the Agentic Development Era

    Apr 8, 2026Dmytro UstynovSoftware Engineering AgentsLLM Agent Workflow Optimization

  10. Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios

    Apr 8, 2026Ruida Hu, Xinchen Wang, Chao Peng +2Code GenerationCode Generation Evaluation

  11. SW-A2A^2-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web

    Apr 5, 2026Linyao Chen, Bo Huang, Qinlao Zhao +13Agentic Code GenerationWeb Agents

  12. CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

    Apr 1, 2026Tara Saba, Zhiyang Chen, Jikai Jason Li +3GPU Kernel GenerationGPU Kernel Optimization

  13. KAT-Coder-V2 Technical Report

    Mar 29, 2026Fengxiang Li, Han Zhang, Haoyang Huang +43AI Coding AgentsAgentic Code Generation

  14. CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation

    Mar 27, 2026Jesse Barkley, Rumi Loghmani, Amir Barati FarimaniText-to-CAD GenerationAgentic Code Generation

  15. ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation

    Mar 26, 2026Jiseung Hong, Benjamin G. Ascoli, Jinho D. ChoiRepository-Level Code GenerationCode Generation Evaluation

  16. SEVerA: Verified Synthesis of Self-Evolving Agents

    Mar 26, 2026Debangshu Banerjee, Changming Xu, Eugene Ie +5Agentic Code GenerationSelf-Evolving Agents

  17. AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation

    Mar 25, 2026Zaid Abulawi, Zavier Ndum Ndum, Eric Cervi +2Scientific Code GenerationAgentic Code Generation

  18. Customized User Plane Processing via Code Generating AI Agents for Next Generation Mobile Networks

    Mar 24, 2026Xiaowen Ma, Onur Ayan, Yunpu Ma +1Code GenerationAgentic Code Generation

  19. Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?

    Mar 23, 2026Oscar Novo, Oscar Bastidas-Jossa, Alberto Calvo +2LLM Code GenerationKnowledge Augmentation for Language Models

  20. DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation

    Mar 22, 2026Shuai Wang, Dhasarathy Parthasarathy, Robert Feldt +1Case-Based ReasoningCode Generation

  21. Exploring the Agentic Frontier of Verilog Code Generation

    Mar 19, 2026Patrick Yubeaton, Siddharth Garg, Chinmay HegdeCode GenerationAgentic Code Generation

  22. SEMAG: Self-Evolutionary Multi-Agent Code Generation

    Mar 16, 2026Yulin Peng, Haowen Hou, Xinxin Zhu +2Agentic Code GenerationLLM Code Generation

  23. Context is all you need: Towards autonomous model-based process design using agentic AI in flowsheet simulations

    Mar 13, 2026Pascal Schäfer, Lukas J. Krinke, Martin Wlotzka +1Agentic WorkflowsAgentic Code Generation

  24. MOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem

    Mar 5, 2026Mengnan Li, Jason Miller, Zaid Abulawi +7AI Agent ReliabilityAgentic Code Generation

  25. Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development

    Mar 3, 2026Matteo Casserini, Alessandro Facchini, Andrea FerrarioAI Agent MonitoringSoftware Engineering Agents