Papers with Code 아카이브
Code Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 28
- 보존된 평가 기록
- 241
Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.
Source: Deep Learning for Source Code Modeling and Generation
Image source: Measuring Coding Challenge Competence With APPS
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
GameDevBench: Evaluating Agentic Capabilities Through Game Development
Libra: Training the Environment for Agentic Information Retrieval
Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection
ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation
Constructing Epistemic AI Literacy: Detecting Epistemic Aims and Processes in Student-AI Co-Programming
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
ASPIRE: Agentic /Skills Discovery for Robotics
LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution
Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows
Self-Evolving Agents with Anytime-Valid Certificates
SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests
Agentic generation of verifiable rules for deterministic, self-expanding reaction classification
Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Human-Agent Collaborative Paper-to-Page Crafting
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas
ComAct: COM-as-Action 패러다임을 통한 전문 소프트웨어 조작의 재정의
멀티 블록 확산 언어 모델
결과 보상 모델을 통한 Text-to-SQL의 테스트 타임 검증
이기종 엔터프라이즈 데이터베이스에서 자연어-SQL 변환을 위한 시맨틱 층 매개 에이전트
AutoTrainess: 언어 모델이 언어 모델을 자율적으로 개선하도록 가르치기
LLM 에이전트를 위한 생성적 스킬 구성
Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents
AI-Assisted Discovery of Convex Relaxations via Dual Agents
Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling
Benchmarking Large Language Models on Floating-Point Error Classification
DA-Studio: An Agentic System for End-to-End Data Analysis
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.