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 111120 of 423 papers

TitleStatusHype
Dynamic Neural Program Embeddings for Program Repair0
Efficient Pragmatic Program Synthesis with Informative Specifications0
EgoCoder: Intelligent Program Synthesis with Hierarchical Sequential Neural Network Model0
Procedural Adherence and Interpretability Through Neuro-Symbolic Generative Agents0
Dreaming with ARC0
A Divide-Align-Conquer Strategy for Program Synthesis0
NESTER: An Adaptive Neurosymbolic Method for Causal Effect Estimation0
Can LLMs plan paths with extra hints from solvers?0
Bayesian Program Learning by Decompiling Amortized Knowledge0
BizBench: A Quantitative Reasoning Benchmark for Business and Finance0
Show:102550
← PrevPage 12 of 43Next →

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