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

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

NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines
Feb 13, 2026Guoan Wang, Shihao Yang, Feng LiuEvolutionary Optimization EEG Decoding
Department of Industrial and Systems Engineering, Rutgers, The State University of New Jersey, 96 Frelinghuysen Road, Piscataway, NJ 08854, USA
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
Feb 13, 2026Sein Kim, Sangwu Park, Hongseok Kang +6Large Language Model-Guided Optimization LLM-Based Program Synthesis
KAIST · Microsoft
Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction
Jan 30, 2026Shihao Xia, Mengting He, Haomin Jia +2Autoformalization Program Synthesis
The Pennsylvania State University · University of the Chinese Academy of Sciences · Institute of Computing Technology, Chinese Academy of Sciences
Programming over Thinking: Efficient and Robust Multi-Constraint Planning
Jan 14, 2026Derrick Goh Xin Deik, Quanyu Long, Zhengyuan Liu +2LLM Planning LLM-Based Program Synthesis
Nanyang Technological University, Singapore · Agency for Science, Technology and Research (A*STAR), Singapore
Evolving Programmatic Skill Networks
Jan 7, 2026Haochen Shi, Xingdi Yuan, Bang LiuContinual Learning for LLM Agents LLM-Based Program Synthesis
DIRO & Institut Courtois, Université de Montréal · Mila – Québec AI Institute · Microsoft Research +1
Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search
Dec 31, 2025Rohit Dwivedula, Divyanshu Saxena, Sujay Yadalam +3Automated Heuristic Design LLM-Based Program Synthesis
The University of Texas at Austin Austin, TX, USA
Compositional Machine Design as Program Synthesis with LLMs
Oct 16, 2025Wenqian Zhang, Yangyi Huang, Weiyang Liu +1LLM-Based Program Synthesis Program Synthesis
The Chinese University of Hong Kong, Shenzhen · The Chinese University of Hong Kong
LLM Priors for ERM over Programs
Oct 16, 2025Shivam Singhal, Priyadarsi Mishra, Eran Malach +1LLM-Based Program Synthesis Empirical Risk Minimization
Department of Computer Science & Engineering, Texas A&M University, TX, USA · Kempner Institute, Harvard University, MA, USA
Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny
Jul 22, 2025Chuanhao Yan, Fengdi Che, Xuhan Huang +12RL for Language Models RL for Language Model Reasoning
Shanghai AI Lab · Tsinghua University · University of Alberta +5
ChatModel: Automating Reference Model Design and Verification with LLMs
Jun 18, 2025Jianmin Ye, Tianyang Liu, Qi Tian +3LLM-Based Program Synthesis LLM Code Generation
National Center of Technology Innovation for EDA, China · School of Integrated Circuits, Southeast University, China
OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
Jul 29, 2024Ali AhmadiTeshnizi, Wenzhi Gao, Herman Brunborg +3Mixed-Integer Linear Programming Large Language Model-Guided Optimization
a School of Management Science and Engineering, Stanford University, Stanford, California 94305 · b Institute for Computational and Mathematical Engineering, Stanford University, Stanford, California 94305

Feb 13, 2026J/K move · Enter open · S save

NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines

Guoan Wang, Shihao Yang, Feng Liu

Department of Industrial and Systems Engineering, Rutgers, The State University of New Jersey, 96 Frelinghuysen Road, Piscataway, NJ 08854, USA

Evolutionary Optimization EEG Decoding Large Language Model-Guided Optimization LLM-Based Program Synthesis Automated Machine Learning

Open paper AskPDF arXiv

Although foundation models have achieved remarkable success in general domains, applying them to electroencephalography (EEG) analysis is constrained by substantial data requirements and large parameter counts, which incur prohibitive computational costs and impede deployment in resource-constrained clinical environments. General-purpose automated machine learning frameworks are likewise ill-suited to this domain, since exploration within an unbounded programmatic space fails to incorporate essential neurophysiological priors and frequently yields neuroscientifically implausible solutions. We therefore propose NeuroWeaver, a unified autonomous evolutionary agent that generalizes across diverse EEG datasets and tasks by reformulating pipeline engineering as a discrete constrained optimization problem solved through large language model (LLM)-driven generation of executable code. A Domain-Informed Subspace Initialization confines the search to a neuroscientifically plausible manifold, while a Multi-Objective Evolutionary Optimization dynamically balances performance, novelty, and efficiency via self-reflective refinement. Across five heterogeneous benchmarks, NeuroWeaver synthesizes lightweight pipelines that outperform state-of-the-art task-specific methods on nearly all metrics and attain accuracy comparable to large-scale foundation models, even surpassing them on the HMC and Workload benchmarks with only

0.18

M and

0.011

M parameters, respectively.