Agentic Code Generation

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 175% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs
Jul 6, 2026Gabriel Poesia, Simon Henniger, Tzu-Han Hsu +2Code Generation LLM-Based Program Synthesis
Kempner Institute, Harvard University · School of Engineering and Applied Sciences, Harvard University
Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study
Jul 2, 2026Achint MehtaAI Agent Reliability Test-Time Scaling
TrendAI
AxDafny: Agentic Verified Code Generation in Dafny
Jun 30, 2026Benjamin Breen, Austin Letson, Borja Requena Pozo +1Code Generation Formal Verification
Axiomatic AI, Boston, MA, USA.
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
Jun 29, 2026Wenjia Jiang, Zongyuan Cai, Yuanhang Shao +7Continual Learning for LLM Agents LLM Agent Self-Improvement
University of Alberta · Southeast University · Virginia Tech +2
Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
Jun 17, 2026Anoushka Vyas, Aarushi Dhanuka, Sina Khoshfetrat Pakazad +1AI Coding Agents Agentic Code Generation
C3 AI
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
Jun 16, 2026Tongxu Luo, Rongsheng Wang, Jiaxi Bi +22AI Agent Benchmarks Agentic Code Generation
1The Chinese University of Hong Kong, Shenzhen · 2Shenzhen Loop Area Institute · 4USTB +5
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
Jun 14, 2026Xuanle Zhao, Qiushi Sun, Jingyu Xiao +16Scientific Visualization Code Generation
Meituan · The University of Hong Kong · The Chinese University of Hong Kong +7
AgentRivet: an automated system for producing Rivet routines from journal publications
Jun 11, 2026Antonio J. Costa, Caterina Doglioni, Christian Gütschow +2Software Engineering Agents Code Generation
Department of Physics & Astronomy, University of Manchester, Manchester M13 9PL, United Kingdom · Centre for Advanced Research Computing, University College London, London WC1E 6BT, United Kingdom
Understanding the Rejection of Fixes Generated by Agentic Pull Requests -- Insights from the AIDev Dataset
Jun 11, 2026Mahmoud Abujadallah, Ali Arabat, Mohammed SayaghAgentic Code Generation Human-AI Collaboration
École de Technologie Supérieure Montréal, Canada
Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
Jun 11, 2026Ali Arabat, Mohammed SayaghSoftware Engineering Agents Agentic Code Generation
École de Technologie Supérieure Montréal, Canada
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
Jun 11, 2026Saehun Chun, Wonje Choi, Sera Choi +2LLM-Based Program Synthesis Agentic Code Generation
Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea.
Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation
Jun 4, 2026Mohammad Zare, Omid AbdolrahmaniAI Coding Agents Agentic Code Generation
Artificial Intelligence Laboratory at AriooBarzan Engineering Team, Shiraz, Iran
EstRTL: Functional Estimation Guided RTL Code Generation
Jun 1, 2026Qi Xiong, Renzhi Chen, Bowei Wang +3Code Generation Agentic Code Generation
College of Computer Science and Technology, National University of Defense Technology, Changsha, China · Defense Innovation Institute, Academy of Military Science (AMS), Beijing, China · School of Computer Science and Technology, Shandong University, Qingdao, China +2
CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space
May 30, 2026Hung Q. Vo, Huy Q. Vo, Son T. Ly +6Computational Pathology Spatial Transcriptomics
University of Houston, Department of Electrical and Computer Engineering, Houston, Texas, 77004, USA · Houston Methodist Hospital, Department of Systems Medicine and Biomedical Engineering, Houston, Texas, 77030, USA
Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation
May 27, 2026Melih Catal, Alex Wolf, Tiago Ferreiro Matos +2Agentic Code Generation Algorithmic Bias
University of Zurich · University of Mannheim
From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence
May 27, 2026Raffael Theiler, Ludovico Comito, David Leko +3Agentic Code Generation ML Reproducibility
EPFL · University of Roma “La Sapienza”
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
May 18, 2026Yixuan Yang, Zhen Luo, Wanshui Gan +5LLM-Based Program Synthesis Agentic Code Generation
Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institute · Southern University of Science and Technology +1
A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
May 18, 2026Anika Tabassum, Md Sifat Hossain, Md. Fahim Arefin +2LLM Self-Refinement Execution-Guided Code Generation
Dept. of Computer Science and Engineering, University of Dhaka, Bangladesh · Dept. of Information Systems, University of Maryland, Baltimore County, USA
Coding Agent Is Good As World Simulator
May 14, 2026Hongyu Wang, Jingquan Wang, Bocheng Zou +2Robotics Simulation World Models
Department of Mechanical & Aerospace Engineering, University of Wisconsin-Madison · School of Computer, Data, and Information Sciences, University of Wisconsin-Madison
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
May 13, 2026Mingzhi Zhu, Michele Merler, Raju Pavuluri +1Software Engineering Agents Agentic Code Generation
Rensselaer Polytechnic Institute Troy, NY 12180 · IBM Research Yorktown Heights, NY 10598
Nautilus: From One Prompt to Plug-and-Play Robot Learning
May 12, 2026Yufeng Jin, Jianfei Guo, Xiaogang Jia +8Robotic Policy Evaluation Agentic Code Generation
1TU Darmstadt · 6Independent Researcher · 2KIT +3
Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering Methodology
May 6, 2026Andrew ZiglerLLM Planning Agentic Code Generation
LinearB Los Angeles, USA
Architectural Constraints Alignment in AI-assisted, Platform-based Service Development
May 6, 2026Julius Irion, Moritz Leugers, Paul Hartwig +5Software Engineering Code Generation
1Technische Universität Berlin, Germany · 2Information Systems Engineering, Technische Universität Berlin, Germany
AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
May 4, 2026Yuecai Zhu, Nikolaos Tsantalis, Peter C. RigbySoftware Engineering LLM Auditing
Department of Computer Science and Software Engineering Concordia University Montréal, Québec, Canada
Social Bias in LLM-Generated Code: Benchmark and Mitigation
May 1, 2026Fazle Rabbi, Lin Ling, Song Wang +1Social Bias in Language Models Agentic Code Generation
Concordia University, Montreal, Canada · Lassonde School of Engineering, York University, Toronto, Canada
HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs
Apr 30, 2026Chang-Chih Meng, Yu-Ren Lu, Guan-Yu Lin +3Electronic Design Automation LLM-Based Program Synthesis
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
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 AI Agentic Code Generation
Independent Researcher · University of Manchester, UK · Idiap Research Institute, Switzerland +1
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 Grounding Scientific Code Generation
Center for Proteomics and Metabolomics, Leiden University Medical Center, Leiden, Netherlands · National Institute of Standards and Technology - Charleston, Charleston, SC USA
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 Agents Agentic Code Generation
University Hospital Aachen, Department of Diagnostic and Interventional Radiology, 52074 Aachen, Germany · Juelich AI Factory, Forschungszentrum Jülich, Jülich, Germany · Else Kröner Fresenius Center for Digital Health, TU Dresden, Dresden, Germany +2
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
Apr 16, 2026Alexey Khoroshilov, Alexey Chernysh, Orkhan Ekhtibarov +2Agentic Code Generation Code Generation Evaluation
Lime

Jul 6, 2026, cs.AIJ/K move · Enter open · S save

Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs

Gabriel Poesia, Simon Henniger, Tzu-Han Hsu, Yilun Du+1

Kempner Institute, Harvard University · School of Engineering and Applied Sciences, Harvard University

Code Generation LLM-Based Program Synthesis Formal Verification Agentic Code Generation Synthetic Data Generation for Language Models

Open paper AskPDF arXiv

The cost of producing code is rapidly diminishing with increasingly capable AI agents, while quality assurance of generated programs has not kept pace. Formal verification provides the strongest possible guarantees, but the ability of AI models to work with verification-aware languages is hindered by the scarcity of human-written examples of programs in those languages. To tackle this prevalent data scarcity issue, we propose Formal Disco: a distributed system for coordination of LLM-based workers that can be easily applied to open-ended synthetic data generation at scale. We use Formal Disco to share tasks and programs between three classes of workers: "initiators", which read random READMEs from open-source repositories and documentation snippets to sketch a related verified program, "fixers" which take compiler and verifier feedback and attempt to resolve issues, and "extenders" that take working programs and propose patches to expand them. Formal Disco records all agent-generated traces and uses them both for initial distillation from a stronger model as well as self-improvement. We also propose a principle of maximum entropy for synthetic program generation, and use entropy maximization via iterative supervised fine-tuning to learn to generate increasingly diverse programs over time. We release large datasets of synthetic verified programs in three languages - Dafny, Verus, and Frama-C -, and fine-tune open models for verification-relevant tasks, often matching or exceeding the performance of Claude Opus 4.5. Overall, our work offers a path to create synthetic data at scale for formal reasoning domains and overcome the long-standing data barrier.

Momentum

Related topics

Latest papers 66