Program Synthesis
139 papers with code • 3 benchmarks • 5 datasets
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.
Libraries
Use these libraries to find Program Synthesis models and implementationsSubtasks
Latest papers with no code
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
Our method iterates between 1) program sampling and hindsight relabeling, and 2) learning from prioritized experience replay.
Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases
Unlike most prior work on indoor scene generation, our system does not require a large training dataset of existing 3D scenes.
Runtime phylogenetic analysis enables extreme subsampling for test-based problems
We introduce phylogeny-informed subsampling, a new class of subsampling methods that exploit runtime phylogenetic analyses for solving test-based problems.
Learning logic programs by finding minimal unsatisfiable subprograms
The goal of inductive logic programming (ILP) is to search for a logic program that generalises training examples and background knowledge.
3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?
Recent advancements in implicit 3D representations and generative models have markedly propelled the field of 3D object generation forward.
LLM4TDD: Best Practices for Test Driven Development Using Large Language Models
In today's society, we are becoming increasingly dependent on software systems.
Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines
On the other hand, representing RL policies using state machines (Inala et al., 2020) can inductively generalize to long-horizon tasks; however, it struggles to scale up to acquire diverse and complex behaviors.
Function-constrained Program Synthesis
Generating computer programs in general-purpose programming languages like Python poses a challenge for LLMs when instructed to use code provided in the prompt.
Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback
Hence, the focus of our work is to leverage open-source code LLMs to generate helpful feedback with correct guidance for code editing.
BizBench: A Quantitative Reasoning Benchmark for Business and Finance
We demonstrate that the current bottleneck in performance is due to LLMs' limited business and financial understanding, highlighting the value of a challenging benchmark for quantitative reasoning within this domain.