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

Showing 5175 of 423 papers

TitleStatusHype
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree SearchCode1
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem SolvingCode1
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
PoE-World: Compositional World Modeling with Products of Programmatic ExpertsCode1
Goals as Reward-Producing ProgramsCode1
ANPL: Towards Natural Programming with Interactive DecompositionCode1
LambdaBeam: Neural Program Search with Higher-Order Functions and LambdasCode1
CodeUpdateArena: Benchmarking Knowledge Editing on API UpdatesCode1
H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus BenchmarkCode1
CrossBeam: Learning to Search in Bottom-Up Program SynthesisCode1
CLEVER: A Curated Benchmark for Formally Verified Code GenerationCode1
Improving Molecular Design by Stochastic Iterative Target AugmentationCode1
Incremental Sampling Without Replacement for Sequence ModelsCode1
CodeScholar: Growing Idiomatic Code ExamplesCode1
Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive GrammarsCode1
Large Language Models for Code: Security Hardening and Adversarial TestingCode1
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningCode1
CodeIt: Self-Improving Language Models with Prioritized Hindsight ReplayCode1
A Reinforcement Learning Environment for Mathematical Reasoning via Program SynthesisCode1
Code Building Genetic ProgrammingCode1
CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance ComputingCode1
GPIoT: Tailoring Small Language Models for IoT Program Synthesis and DevelopmentCode1
Data types as a more ergonomic frontend for Grammar-Guided Genetic ProgrammingCode1
Communicating Natural Programs to Humans and MachinesCode1
Show:102550
← PrevPage 3 of 17Next →

Benchmark Results

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