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.

Ranking Function Generation with LLMs for Termination
Oct 26, 2026Rongkang Li, Jiaxin Hu, Taolue Chen +3Program Synthesis LLM-Based Program Synthesis
Key Laboratory of System Software (Chinese Academy of Sciences), China · Institute of Software, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China +2
FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs
Oct 24, 2026Sadra Sabouri, Hosein Hasanbeig, Adam Sage +6LLM Agent Workflow Optimization LLM-Based Program Synthesis
University of Southern California, Los Angeles, CA · Microsoft, Redmond, WA
AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments
Oct 22, 2026Ze-Yu Peng, Qing-Yu Lan, Zhan-He Wang +2LLMs for Evolutionary Optimization LLM-Based Program Synthesis
School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China. · International Centre for Theoretical Physics Asia-Pacific, University of Chinese Academy of Sciences, Beijing 100190, China. · Taiji Laboratory for Gravitational Wave Universe, University of Chinese Academy of Sciences, Beijing 100049, China. +2
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
Oct 20, 2026Ha Minh Hieu, Tongyao Zhu, Do Xuan Long +1Large Language Model-Guided Scientific Discovery LLMs for Evolutionary Optimization
Hanoi University of Science and Technology · National University of Singapore
ABACUS: Program-Guided Multistep Reasoning over Frozen Judgment Models
Oct 19, 2026Yuhao Wang, Zelin ZangStructured Reasoning in Language Models Efficient Language Model Reasoning
Westlake University · Hong Kong Institute of Science & Innovation, CAS · Tsientang Institute for Advanced Study
Maestro: Agentic Formal Proof Development by Coordination
Oct 19, 2026Haoyu Li, Zeren Shui, Yuhao Zhang +4Large Language Model-Guided Theorem Proving Lean Theorem Proving
University of Illinois Urbana-Champaign · AWS AI Labs · Georgia Institute of Technology
PRECOCIAL: Pretraining with Code Curriculums via Iterative Search for Accelerated Learning
Oct 18, 2026Edward Gu, Ali Payani, Kevin EllisSynthetic Data Pretraining Synthetic Data Generation for Language Models
Cornell University · Cisco Research
Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning
Oct 17, 2026Kyuyoung Kim, Zilin Xiao, Zhiyuan Wang +4Retrieval-Augmented Reasoning RL for RAG
KAIST AI · Meta Superintelligence Labs
Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models
Oct 16, 2026Koki Takeshita, Kenji Uebayashi, Hikaru Tomonari +6RTL Code Generation Electronic Design Automation
Research & Development Group, Hitachi, Ltd.
Compiling Expert Procedures into Verified Programs: When a Small Model Is Enough
Oct 13, 2026Vishvesh Bhat, Asad Aali, Muhammad Ahmed MohsinLLM Tool Use LLM-Based Program Synthesis
CoreThink AI · Stanford University
Declarative Reactive Robot Behaviors from Imperative Language Models
Oct 12, 2026Vincent Berenz, Tasha Kim, Bernhard SchölkopfLLM-Based Program Synthesis AI Coding Agents
Max Planck Institute for Intelligent Systems, Tübingen, Germany · University of Oxford, Oxford, United Kingdom · ELLIS Institute Tübingen, Germany +1
Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation
Oct 11, 2026R. Kenny Jones, Jiajun Wu, Maneesh AgrawalaHuman-AI Co-Creation LLM-Based Program Synthesis
Stanford University, USA
TLA-Verus: Generating and Solving Temporal Proof Obligations with LLM Agents
Oct 10, 2026Kseniia Strelbytska, Balázs Szilágyi, Anna Mészáros +1Formal Verification Automated Theorem Proving
Stephen Perse Cambridge, UK · University of Cambridge, UK · Reasonable
LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement
Oct 10, 2026Ruichen Xia, Xiao Han, Dingyu Yang +5LLM-Based Program Synthesis Text-to-SQL
The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Institute of Computing Innovation, Zhejiang University, Hangzhou, China · Zhejiang Geely Holding Group Co., Ltd., Hangzhou, China
VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
Oct 9, 2026Fuqiang Wang, Zheng Guo, Xiaoming Wu +53D Scene Layout Generation LLM-Based Program Synthesis
Qilu University of Technology, Jinan, China · Tianjin University, Tianjin, China · Shandong University, Jinan, China +3
Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
Oct 8, 2026Saurabh Mathur, Sahil Sidheekh, Bhavan Vasu +4Probabilistic Logic Inductive Logic Programming
Technische Universität Darmstadt · The University of Texas at Dallas · AT&T CDO +1
EliteTable: Self-Improving Program Search for Executable Control Policies
Oct 8, 2026Stuart FarmerProgram Synthesis LLM-Based Program Synthesis
Casa Dilauro Independent Research (casadilauro.com)
EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs
Oct 7, 2026Leizhen Wang, Peibo Duan, Zhenlin Qin +5Traffic Signal Control Automated Heuristic Design
Monash University · KTH Royal Institute of Technology · Chinese Academy of Sciences +2
AGAR: a reinforcement learning substrate for LLM program evolution
Oct 6, 2026Haoran Li, Zengle Ge, Xiaomin Yuan +11LLM-Based Program Synthesis RL for Code Generation
University of the Chinese Academy of Sciences · Baidu · Tsinghua University +2
CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency
Oct 6, 2026Kaushal Mhapsekar, Bita Aslrousta, Brijesh Kumar Bhayana +5Large Language Model-Guided Optimization LLM-Based Program Synthesis
Department of Electrical and Computer Engineering North Carolina State University, Raleigh, NC, USA
SimAuthor: Harnessing Foundation Models for Persistent Scientific Simulator Authoring
Oct 5, 2026Yishan Wang, Ran Piao, Mathias Funk +1LLM-Based Program Synthesis Scientific Code Generation
Eindhoven University of Technology
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
Oct 2, 2026Hui Chen, Xuan Qi, James Xu Zhao +5Large Language Model-Guided Optimization Evolutionary Optimization
National University of Singapore · University of Washington · Princeton University +1
PLCWorld: Benchmarking LLM-Generated PLC Programs in Closed-Loop Plant Simulation
Oct 2, 2026Yunji Kim, Yunseok Lee, Hyunwoo Seo +2LLM-Based Program Synthesis Code Generation
Dongguk University · MOAI technologies
Self-Supervised Scaling of Terminal Environments for Scientific Domains
Oct 2, 2026Zhongzhi Li, Yucheng Shi, Zongxia Li +8Terminal Agents LLM Agent Training
Tencent HY LLM Frontier · University of Georgia · University of Maryland, College Park +4
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
Oct 1, 2026David BerghausInterpretable Anomaly Detection LLM-Based Program Synthesis
Lamarr Institute Germany · Fraunhofer IAIS Germany
HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols
Oct 1, 2026Farzad Habibi, Juncheng Fang, Faisal NawabLarge Language Model-Guided Optimization LLM-Based Program Synthesis
University of California, Irvine
LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery
Sep 30, 2026Bo Yuan, Wenqian Ye, Zelin Zhao +4Automated Algorithm Discovery LLM-Based Program Synthesis
Georgia Institute of Technology · University of Virginia, Charlottesville
MatLoom: Layered Text-to-Material Generation in a Compact Program Space
Sep 30, 2026Anson Y. Lam, Shuqing Li, Michael R. Lyu3D Asset Generation LLM-Based Program Synthesis
Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong, China
Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests
Sep 30, 2026Tianyu Chen, Yasi Zhang, Ruiyi Wang +3Large Language Model-Guided Optimization LLM-Based Program Synthesis
University of Texas at Austin · University of California, Los Angeles · University of California, San Diego +3
Code to Control: Synthesizing Parameterized Reactive Controllers
Sep 30, 2026Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates +1RL Control Language Model-Based Control
Harvard University · Massachusetts Institute of Technology · Florida Institute for Human and Machine Cognition

Oct 26, 2026J/K move · Enter open · S save

Ranking Function Generation with LLMs for Termination

Rongkang Li, Jiaxin Hu, Taolue Chen, Yong Li+2

Key Laboratory of System Software (Chinese Academy of Sciences), China · Institute of Software, Chinese Academy of Sciences, China · University of Chinese Academy of Sciences, China+2

Program Synthesis LLM-Based Program Synthesis Formal Verification

Open paper AskPDF arXiv

Ranking functions are a fundamental technique for proving loop termination, but constructing them manually is challenging and requires substantial expertise. We propose RAINFALL, a neuro-symbolic framework which follows the generate-verify-refine paradigm and tightly integrates LLMs with symbolic verification. RAINFALL formulates ranking function synthesis as a code-completion task by inserting placeholders into the input program and constraining the LLM to fill four predefined slots for each loop. The completed program is then checked by a symbolic verifier. If verification succeeds, a valid ranking function is obtained; otherwise, the verifier's diagnostics are translated into natural-language feedback that guides iterative refinement of the LLM's output. We evaluate RAINFALL on two public benchmark suites comprising 358 terminating C programs. Using MiniMax V2.7, RAINFALL synthesizes verifiable ranking functions for 323 programs (90.22%), outperforming all promising baselines. In particular, it solves 12 more programs than PROTON 2.1, the best-performing baseline and winner of the SV-COMP 2026 Termination category. Furthermore, combining RAINFALL with PROTON 2.1 increases the success rate to 96.65% (346/358 programs). We also conduct ablation study confirming individual contributions of placeholder contracts, few-shot examples, symbolic verification, and diagnostic information feedback. Experiments across LLMs further confirm the effectiveness of RAINFALL. Our results suggest a generic, sound framework for ranking-function synthesis and, beyond termination, LLM-assisted synthesis of formally checkable liveness certificates, both of which represent new directions of software engineering research.