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 51–100 of 423 papers

TitleStatusHype
Latent Execution for Neural Program SynthesisCode1
SQUARES: A SQL Synthesizer Using Query Reverse EngineeringCode1
Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQACode1
Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code StacksCode1
RLTF: Reinforcement Learning from Unit Test FeedbackCode1
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsCode1
NeuRI: Diversifying DNN Generation via Inductive Rule InferenceCode1
From Examples to Rules: Neural Guided Rule Synthesis for Information ExtractionCode1
Learning programs with magic valuesCode1
GPT-based Open-Ended Knowledge TracingCode1
CodeUpdateArena: Benchmarking Knowledge Editing on API UpdatesCode1
CLEVER: A Curated Benchmark for Formally Verified Code GenerationCode1
LILO: Learning Interpretable Libraries by Compressing and Documenting CodeCode1
MA-RLHF: Reinforcement Learning from Human Feedback with Macro ActionsCode1
Opening the AI black box: program synthesis via mechanistic interpretabilityCode1
CodeScholar: Growing Idiomatic Code ExamplesCode1
Enhancing Network Management Using Code Generated by Large Language ModelsCode1
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design SequencesCode1
Improving Molecular Design by Stochastic Iterative Target AugmentationCode1
Learning to Synthesize Programs as Interpretable and Generalizable PoliciesCode1
Execution-based Code Generation using Deep Reinforcement LearningCode1
CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance ComputingCode1
CodeIt: Self-Improving Language Models with Prioritized Hindsight ReplayCode1
Explanatory Learning: Beyond Empiricism in Neural NetworksCode1
A Reinforcement Learning Environment for Mathematical Reasoning via Program SynthesisCode1
Code Building Genetic ProgrammingCode1
Communicating Natural Programs to Humans and MachinesCode1
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem SolvingCode1
GPIoT: Tailoring Small Language Models for IoT Program Synthesis and DevelopmentCode1
AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT ApplicationsCode1
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree SearchCode1
Improving Code Generation by Training with Natural Language FeedbackCode1
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningCode1
Goals as Reward-Producing ProgramsCode1
Emergent Representations of Program Semantics in Language Models Trained on ProgramsCode1
Automatic Program Synthesis of Long Programs with a Learned Garbage CollectorCode1
Graphs, Constraints, and Search for the Abstraction and Reasoning CorpusCode1
Learning Program Synthesis for Integer Sequences from ScratchCode1
Automating the Design of Multigrid Methods with Evolutionary Program SynthesisCode1
Guiding Program Synthesis by Learning to Generate ExamplesCode1
AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz TestingCode1
CrossBeam: Learning to Search in Bottom-Up Program SynthesisCode1
Analyzing the Effectiveness of Large Language Models on Text-to-SQL SynthesisCode1
Data types as a more ergonomic frontend for Grammar-Guided Genetic ProgrammingCode1
Less is More: Summary of Long Instructions is Better for Program SynthesisCode1
OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System VerificationCode1
RobustFill: Neural Program Learning under Noisy I/OCode1
Learning logic programs by combining programsCode0
A probabilistic and multi-objective analysis of lexicase selection and epsilon-lexicase selectionCode0
ChatGPT for GTFS: Benchmarking LLMs on GTFS Understanding and RetrievalCode0
Show:102550
← PrevPage 2 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