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 101110 of 423 papers

TitleStatusHype
HumanEval on Latest GPT Models -- 2024Code0
LTL learning on GPUsCode0
WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment0
SwissNYF: Tool Grounded LLM Agents for Black Box SettingCode0
Pix2Code: Learning to Compose Neural Visual Concepts as ProgramsCode1
Opening the AI black box: program synthesis via mechanistic interpretabilityCode1
CodeIt: Self-Improving Language Models with Prioritized Hindsight ReplayCode1
Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases0
Runtime phylogenetic analysis enables extreme subsampling for test-based problems0
ReGAL: Refactoring Programs to Discover Generalizable AbstractionsCode1
Show:102550
← PrevPage 11 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