SOTAVerified

Program Synthesis

Program synthesis is the process of automatically generating a program or code snippet that satisfies a given specification or set of requirements. This can include generating code from a formal specification, a natural language description, or example inputs and outputs. The primary goal of program synthesis is to minimize human intervention in the coding process, reduce errors, and improve productivity.

Program synthesis often involves the use of advanced algorithms, artificial intelligence, and machine learning techniques to search the space of possible programs that meet the given constraints. This process can be guided by a variety of techniques, such as constraint solving, symbolic execution, and genetic algorithms.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 423 papers

TitleStatusHype
LambdaBeam: Neural Program Search with Higher-Order Functions and LambdasCode1
Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion—0
ANPL: Towards Natural Programming with Interactive DecompositionCode1
Search-Based Regular Expression Inference on a GPUCode1
Coarse-Tuning Models of Code with Reinforcement Learning Feedback—0
Learning-Based Automatic Synthesis of Software Code and Configuration—0
Gorilla: Large Language Model Connected with Massive APIsCode6
Probabilistic Lexicase SelectionCode0
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingCode0
Emergent Representations of Program Semantics in Language Models Trained on ProgramsCode1
Learning to Parallelize with OpenMP by Augmented Heterogeneous AST RepresentationCode0
CodeGen2: Lessons for Training LLMs on Programming and Natural LanguagesCode5
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code GenerationCode3
A Survey of Methods for Converting Unstructured Data to CSG Models—0
From Words to Code: Harnessing Data for Program Synthesis from Natural Language—0
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code GenerationCode1
(Vector) Space is Not the Final Frontier: Product Search as Program Synthesis—0
Fully Autonomous Programming with Large Language Models—0
Untangling the Effects of Down-Sampling and Selection in Genetic Programming—0
ImageEye: Batch Image Processing Using Program Synthesis—0
HOTGP -- Higher-Order Typed Genetic Programming—0
Improving Code Generation by Training with Natural Language FeedbackCode1
WikiCoder: Learning to Write Knowledge-Powered CodeCode1
Improved Tree Search for Automatic Program Synthesis—0
Hierarchical Neural Program Synthesis—0
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and RetrievalCode1
A Neurodiversity-Inspired Solver for the Abstraction \& Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis—0
Complex QA and language models hybrid architectures, Survey—0
Large Language Models for Code: Security Hardening and Adversarial TestingCode1
Down-Sampled Epsilon-Lexicase Selection for Real-World Symbolic Regression Problems—0
Exploring Data Augmentation for Code Generation TasksCode0
NeuRI: Diversifying DNN Generation via Inductive Rule InferenceCode1
Execution-based Code Generation using Deep Reinforcement LearningCode1
PADL: Language-Directed Physics-Based Character ControlCode1
MTGP: Combining Metamorphic Testing and Genetic Programming—0
A Divide-Align-Conquer Strategy for Program Synthesis—0
Informed Down-Sampled Lexicase Selection: Identifying productive training cases for efficient problem solving—0
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities—0
Parsel: Algorithmic Reasoning with Language Models by Composing DecompositionsCode2
Genetic Algorithm for Program Synthesis—0
Programming by Example and Text-to-Code Translation for Conversational Code Generation—0
NESTER: An Adaptive Neurosymbolic Method for Causal Effect Estimation—0
Large Language Models Are Human-Level Prompt EngineersCode3
Synthesizing Programs with Continuous Optimization—0
Generating Sequences by Learning to Self-Correct—0
Graphs, Constraints, and Search for the Abstraction and Reasoning CorpusCode1
Data types as a more ergonomic frontend for Grammar-Guided Genetic ProgrammingCode1
Relational program synthesis with numerical reasoningCode1
Neural-Guided Program Synthesis of Information Extraction Rules Using Self-Supervision—0
Toward Trustworthy Neural Program Synthesis—0
Show:102550
← PrevPage 4 of 9Next →
All datasetsSPoC TestPSPoC TestWAlgoLisp

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DrRepairSuccess rate @budget 10038.5—Unverified
2Multiclass localizerSuccess rate @budget 10034.2—Unverified
#ModelMetricClaimedVerifiedStatus
1DrRepairSuccess rate @budget 10057—Unverified
2Multiclass localizerSuccess rate @budget 10053.7—Unverified
#ModelMetricClaimedVerifiedStatus
1CodeTrans-MT-TF-SmallAccuracy90.31—Unverified