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 101–150 of 423 papers

TitleStatusHype
A probabilistic and multi-objective analysis of lexicase selection and epsilon-lexicase selectionCode0
ChatGPT for GTFS: Benchmarking LLMs on GTFS Understanding and RetrievalCode0
Relational decomposition for program synthesisCode0
P-Tree ProgrammingCode0
Enhancing Code Generation via Bidirectional Comment-Level Mutual GroundingCode0
Recent Advances in Neural Program SynthesisCode0
Program Synthesis Dialog Agents for Interactive Decision-MakingCode0
Program Synthesis and Semantic Parsing with Learned Code IdiomsCode0
Program Synthesis as Dependency Quantified Formula Modulo TheoryCode0
Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning TestCode0
Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology ProblemsCode0
Dynamic Neural Program Embedding for Program RepairCode0
PLANS: Robust Program Learning from Neurally Inferred SpecificationsCode0
Adaptive Correlated Monte Carlo for Contextual Categorical Sequence GenerationCode0
BF++: a language for general-purpose program synthesisCode0
PanGu-Coder: Program Synthesis with Function-Level Language ModelingCode0
Probabilistic Lexicase SelectionCode0
Evaluating Sequence-to-Sequence Learning Models for If-Then Program SynthesisCode0
Differentiable Functional Program InterpretersCode0
Novel positional encodings to enable tree-based transformersCode0
Neural Program Synthesis from Diverse Demonstration VideosCode0
Neural Guided Constraint Logic Programming for Program SynthesisCode0
Neural Program Synthesis with Priority Queue TrainingCode0
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement LearningCode0
NAPS: Natural Program Synthesis DatasetCode0
DeepCoder: Learning to Write ProgramsCode0
Memory Augmented Policy Optimization for Program Synthesis and Semantic ParsingCode0
Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural RepresentationsCode0
DALex: Lexicase-like Selection via Diverse AggregationCode0
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingCode0
Making sense of sensory inputCode0
Analysis of Evolutionary Program Synthesis for Card GamesCode0
Automatic Synthesis of Diverse Weak Supervision Sources for Behavior AnalysisCode0
LTL learning on GPUsCode0
Learning to Infer Program SketchesCode0
Learning to Execute Programs with Instruction Pointer Attention Graph Neural NetworksCode0
Learning to Infer Graphics Programs from Hand-Drawn ImagesCode0
Learning to Parallelize with OpenMP by Augmented Heterogeneous AST RepresentationCode0
ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)Code0
Learning logic programs by combining programsCode0
Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning EnvironmentsCode0
Learning to Reason via Program Generation, Emulation, and SearchCode0
Amortizing Pragmatic Program Synthesis with RankingsCode0
Learning logic programs by discovering higher-order abstractionsCode0
Autoencoders as Tools for Program SynthesisCode0
Learning logic programs by discovering where not to searchCode0
Coffee: Boost Your Code LLMs by Fixing Bugs with FeedbackCode0
Large Language Models Synergize with Automated Machine LearningCode0
Generating Programmatic Referring Expressions via Program SynthesisCode0
Generating Pragmatic Examples to Train Neural Program SynthesizersCode0
Show:102550
← PrevPage 3 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