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 51–75 of 423 papers

TitleStatusHype
Search-Based Regular Expression Inference on a GPUCode1
Emergent Representations of Program Semantics in Language Models Trained on ProgramsCode1
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code GenerationCode1
Improving Code Generation by Training with Natural Language FeedbackCode1
WikiCoder: Learning to Write Knowledge-Powered CodeCode1
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and RetrievalCode1
Large Language Models for Code: Security Hardening and Adversarial TestingCode1
NeuRI: Diversifying DNN Generation via Inductive Rule InferenceCode1
PADL: Language-Directed Physics-Based Character ControlCode1
Execution-based Code Generation using Deep Reinforcement LearningCode1
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
Learning programs with magic valuesCode1
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsCode1
CrossBeam: Learning to Search in Bottom-Up Program SynthesisCode1
Less is More: Summary of Long Instructions is Better for Program SynthesisCode1
Learning Program Synthesis for Integer Sequences from ScratchCode1
GPT-based Open-Ended Knowledge TracingCode1
Explanatory Learning: Beyond Empiricism in Neural NetworksCode1
From Examples to Rules: Neural Guided Rule Synthesis for Information ExtractionCode1
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human LevelCode1
Scaling Neural Program Synthesis with Distribution-based SearchCode1
Learning to Synthesize Programs as Interpretable and Generalizable PoliciesCode1
Program Synthesis with Large Language ModelsCode1
Show:102550
← PrevPage 3 of 17Next →
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