LLM-Based Program Synthesis

Follow this topic Ask about this topic

This field studies how language models can turn descriptions, examples, or formal specifications into programs, algorithms, and executable workflows. Common approaches combine prompting or specialized intermediate languages with retrieval, multi-agent decomposition, evolutionary search, and feedback from execution, solvers, compilers, or formal verifiers. These methods are used for tasks ranging from benchmark coding and Dafny or Verilog generation to optimization, GPU kernels, robotics, and CAD; evaluation often tests execution and correctness on suites such as LiveCodeBench, KernelBench, and VerilogEval. Systems can produce useful domain-specific code, but passing tests or compiling does not ensure semantic correctness, safety, performance, or generalization to unseen cases.

Latest papers

311 papers36 papers in the last four weeks, up 24% on the four weeks before. 0.2% of all new papers.

SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
Apr 27, 2026Sichun Luo, Yi Huang, Haochen Luo +7Automated Algorithm Discovery Evolutionary Optimization
1The University of Hong Kong · 2JIUTIAN Research, China Mobile · 3City University of Hong Kong
RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation
Apr 27, 2026Yifan Zhang, Jianmin Ye, Jiahao Yang +1Electronic Design Automation LLM-Based Program Synthesis
School of Integrated Circuits, Southeast University, China · National Center of Technology Innovation for EDA, China
A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees
Apr 27, 2026Bin Chen, Shouliang Zhu, Beidan Liu +4Automated Algorithm Discovery Automated Heuristic Design
The Institute of Intelligent Computing, University of Electronic Science and Technology of China, Chengdu 611731, China · College of Systems Engineering, National University of Defense Technology, Changsha 410073, China · Academy of Military Medical Sciences, Beijing 100071, China
PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
Apr 26, 2026Tianyidan Xie, Peiyu Wang, Hu Jiaxin +9LLM-Based Program Synthesis Scientific Code Generation
Nanjing University · Skywork AI · Jilin University +2
AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs
Apr 24, 2026Pouya Pezeshkpour, Estevam HruschkaLLM Evaluation LLM Answer Verification
Megagon Labs
From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
Apr 24, 2026Md Erfan, Md Kamal Hossain Chowdhury, Ahmed Ryan +1LLM Prompting Code Generation
Department of Computer Science, The University of Alabama, Tuscaloosa, USA · Alabama Water Institute, The University of Alabama, Tuscaloosa, USA
Streamliners for Answer Set Programming
Apr 21, 2026Florentina Voboril, Martin Gebser, Stefan Szeider +1Logic Programming Large Language Model-Guided Optimization
TU Wien Vienna, Austria · University of Klagenfurt Klagenfurt, Austria
PARM: Pipeline-Adapted Reward Model
Apr 20, 2026Xingyu Fan, Wei Shao, Jiacheng Liu +2Reward Modeling LLM-Based Program Synthesis
SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution
Apr 20, 2026Woojin Lee, Jin-Xia HuangProperty-Based Testing Execution-Guided Code Generation
Electronics and Telecommunications Research Institute, Republic of Korea
Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics
Apr 20, 2026Khang Tran, Khoa Nguyen, Cristian Borcea +1LLM-Based Program Synthesis Automated Test Generation
New Jersey Institute of Technology, Newark, NJ, USA
Probabilistic Programs of Thought
Apr 19, 2026Poorva Garg, Renato Lui Geh, Daniel Israel +3LLM-Based Program Synthesis Efficient Language Model Reasoning
University of California Los Angeles · Allen Institute for AI
Certified Program Synthesis with a Multi-Modal Verifier
Apr 17, 2026Yueyang Feng, Dipesh Kafle, Vladimir Gladshtein +5Property-Based Testing LLM-Based Program Synthesis
National University of Singapore · Singapore · Neapolis University Pafos +2
Neurosymbolic Repo-level Code Localization
Apr 17, 2026Xiufeng Xu, Xiufeng Wu, Zejun Zhang +1Software Engineering Benchmarks LLM-Based Program Synthesis
Nanyang Technological University, Singapore
EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs
Apr 17, 2026David BerghausEvent Time Prediction Time Series Imputation
Lamarr Institute · Fraunhofer IAIS
ARGUS: Agentic GPU Optimization Guided by Data-Flow Invariants
Apr 16, 2026Haohui Mai, Xiaoyan Guo, Xiangyun Ding +7GPU Kernel Optimization GPU Acceleration
UC Riverside5 · UCAS4 · Tsinghua University2 +2
COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation
Apr 16, 2026Heng Ping, Peiyu Zhang, Shixuan Li +5Multi-Objective Evolutionary Optimization Code Generation
University of Southern California United States
VeriGraphi: A Multi-Agent Framework of Hierarchical RTL Generation for Large Hardware Designs
Apr 16, 2026Sazzadul Islam, Tasnim Tabassum, Hao ZhengLLM Grounding LLM-Based Program Synthesis
Dept. of Computer Science & Eng. University of South Florida Tampa, Florida, United States
E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning
Apr 13, 2026Lingzhe Zhang, Yunpeng Zhai, Tong Jia +5LLM-Based Program Synthesis Microservice Architecture
Peking University; Key Laboratory of Data Intelligence and Security Beijing, China · Alibaba Group China · Peking University; Key Laboratory of Data Space Technology and System Beijing, China
ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation
Apr 13, 2026Yuan Shui, Yandong Guan, Zhanwei Zhang +4Text-to-CAD Generation Parametric CAD Modeling
School of Software, Beihang University · Zhejiang University · The University of Hong Kong
Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction
Apr 11, 2026Qinjuan Wang, Shan Yang, Yongli ZhuAgentic Code Generation LLM-Based Program Synthesis
Sun Yat-sen University, Guangzhou, China
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
Apr 7, 2026Juekai Lin, Yun Zhu, Honglin Lin +6Image-to-Code Generation Code Generation
Zhejiang University Hangzhou, China · Shanghai Artificial Intelligence Laboratory Shanghai, China · Peking University Beijing, China
Arch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware Design
Apr 7, 2026Shuqing ZhaoElectronic Design Automation RTL Code Generation
SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skills
Apr 7, 2026Da Lei, Feng Xiao, Lu Li +1Traffic Signal Control Agent Skill Learning
Business School, Sichuan University, Chengdu, China
ENCRUST: Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation
Apr 6, 2026Hohyun Sim, Hyeonjoong Cho, Ali Shokri +2Code Translation LLM-Based Program Synthesis
Korea University, South Korea · University of Houston, United States · State University of New York Korea, South Korea +1
ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs
Apr 3, 2026Lik Tung Fu, Jie Zhou, Shaokai Ren +6SystemVerilog Assertion Generation Formal Hardware Verification
National ASIC Center, School of Integrated Circuits, Southeast University, China · National Center of Technology Innovation for Electronic Design Automation, China · Department of Computer Science, City University of Hong Kong, Hong Kong, China
Automating Database-Native Function Code Synthesis with LLMs
Apr 2, 2026Wei Zhou, Xuanhe Zhou, Qikang He +4LLM-Based Program Synthesis LLM Code Generation
Shanghai Jiao Tong University, China · Tsinghua University, China · National University of Singapore, Singapore +1
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 Generation GPU Kernel Optimization
Department of Computer Science, University of Toronto · Standard Kernel
Interactive Clarification for Cloud Infrastructure-as-Code Synthesis
Apr 1, 2026Zhenning Yang, Kaden Gruizenga, Tongyuan Miao +4LLM-Based Program Synthesis Cloud Computing
University of Michigan · University of Massachusetts Amherst
Learning to Model Optimization Problems from Solver Outcomes
Apr 1, 2026Runda Guan, Xiangqing Shen, Jiajun Zhang +3Natural Language to Optimization Modeling Learning to Optimize
School of Computer Science and Engineering, Nanjing University of Science and Technology · School of Intelligence Science and Technology, Nanjing University · Institute of Automation, Chinese Academy of Sciences
Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents
Apr 1, 2026Alibek Kaliyev, Artem MaryanskyyAI Agent Reliability Tool-Use Evaluation
The University of Texas at Austin · Austin, Texas, USA · Uber +1

Apr 27, 2026J/K move · Enter open · S save

SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution

Sichun Luo, Yi Huang, Haochen Luo, Fengyuan Liu+6

1The University of Hong Kong · 2JIUTIAN Research, China Mobile · 3City University of Hong Kong

Automated Algorithm Discovery Evolutionary Optimization Large Language Model-Guided Optimization LLM-Based Program Synthesis LLMs for Evolutionary Optimization

Open paper AskPDF arXiv

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when natural-language reasoning is used through heuristic descriptions or reflection, it typically remains transient mutation context or unstructured memory, rather than organized as persistent population-level state over strategic directions. As a result, evolutionary search can struggle to distinguish syntactically different implementations of the same idea, preserve lower-fitness but strategically promising directions, or detect when an entire family of strategies has saturated. We introduce \model, a modular strategy-space layer that turns language-level strategic reasoning into first-class population-level evolutionary state in LLM-driven program search. \model represents each candidate program with an explicit natural-language strategy, clusters the archive by strategy semantics, retrieves behaviorally complementary inspirations, and periodically navigates the strategy landscape to avoid saturated directions. Without modifying the underlying evolutionary algorithms, \model improves existing evolutionary backbones across algorithm discovery, systems optimization, and agent-scaffold design tasks in most settings. Across four systems benchmarks, \model achieves a 20.6% average relative improvement, with the best single run on Prism scoring 3

\times

higher. These results suggest that persistent strategy representations provide a practical mechanism for improving the effectiveness and cost-efficiency of LLM-guided evolutionary search, pointing toward compound AI systems whose search capabilities benefit from the structured accumulation and reuse of algorithmic strategies.