Papers with Code 아카이브
Program Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 3
- 보존된 평가 기록
- 5
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks
$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models
Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories
Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems
SemAgent: A Semantics Aware Program Repair Agent
Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge
SHORE: A Long-term User Lifetime Value Prediction Model in Digital Games
A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair
UniPTMs: The First Unified Multi-type PTM Site Prediction Model via Master-Slave Architecture-Based Multi-Stage Fusion Strategy and Hierarchical Contrastive Loss
Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
Benchmarking and Enhancing LLM Agents in Localizing Linux Kernel Bugs
Chemical classification program synthesis using generative artificial intelligence
Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces
Data Mining-Based Techniques for Software Fault Localization
Mini-Game Lifetime Value Prediction in WeChat
CLEVER: A Curated Benchmark for Formally Verified Code Generation
Transductively Informed Inductive Program Synthesis
PoE-World: Compositional World Modeling with Products of Programmatic Experts
Synthetic Code Surgery: Repairing Bugs and Vulnerabilities with LLMs and Synthetic Data
Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models
QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach
OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification
GPU accelerated program synthesis: Enumerate semantics, not syntax!
SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs
TinyverseGP: Towards a Modular Cross-domain Benchmarking Framework for Genetic Programming
GenEDA: Unleashing Generative Reasoning on Netlist via Multimodal Encoder-Decoder Aligned Foundation Model
DeQompile: quantum circuit decompilation using genetic programming for explainable quantum architecture search
Using ML filters to help automated vulnerability repairs: when it helps and when it doesn't
How Accurately Do Large Language Models Understand Code?
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.