Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outco…
Reinforcement LearningCode GenerationProfiling Lightweight Large Language Models
Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resource-constrained edge and mobile environments. In such settings, energ…
Mathematical ReasoningCode GenerationEvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization
Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such as fast-slow thinking switching and reasoning trajectory compression…
Mathematical ReasoningCode GenerationH^2SD: Hybrid Hindsight Self-Distillation
Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation. However, most RLVR methods…
Reinforcement LearningMathematical ReasoningCode GenerationGroup Entropy-Controlled Policy Optimization
Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm is often conducte…
Reinforcement LearningInstruction FollowingCode GenerationLQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research
Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise required to turn research motivation into…
Code GenerationLarge Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general t…
Code GenerationText GenerationWho Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
Self-evolving agent systems create, revise, and retire their own skills, but every such loop assumes a reliable evaluation metric already exists. In many real applications none does. We show the metric itself can be the …
Code GenerationCommenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications
As AI code tools become integrated into programming environments, students increasingly describe intended behavior in natural language and rely on these tools to generate code, shifting emphasis from code writing to spec…
Code GenerationReinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards
Partial differential equations (PDEs) are foundational to modeling in science and engineering, but constructing reliable numerical solvers remains labor-intensive, demanding expert knowledge of discretization schemes, st…
Reinforcement LearningCode GenerationToward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability
With the rapid development of Large Language Models (LLMs), text watermarking has emerged as a crucial technique for identifying machine-generated content. However, directly applying existing logits-based watermarking me…
Code GenerationOpenProver: Agentic and Interactive Theorem Proving with Lean 4
In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Lean 4 formal verification. OpenProver integrates a Planner-Worker-Verifier architecture i…
Automated Theorem ProvingCode GenerationProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, str…
Semantic SimilaritySemantic RetrievalCode GenerationTool-Making and Self-Evolving LLM Agents in Low-Latency Systems
Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles…
Code GenerationLarge Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutioni…
Adversarial DefenseFederated LearningAnomaly DetectionCode Generationfog: Expressing Motion and Emotion through Function Composition of AI-Generated Code
Motion and emotion are core parts of intelligent, expressive behavior. In this paper, we introduce fog, a function composition framework for implementing and compose motion functions. We demonstrate how fog can be used t…
Code GenerationSelective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation
Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia. Improving Small Langua…
Reinforcement LearningCode GenerationFunctional and Secure Code Generation with Task Vectors
Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities. Prior work to improve the secure code generation abilities of such c…
Code GenerationFreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning. We introd…
Question AnsweringCode GenerationEvaluating Neural Decompilation of Dart AOT Binaries: Fine-Tuning, Metric Validity, Specification Leakage, and Reliability
We present an execution-based evaluation of neural decompilation for Dart ahead-of-time binaries and an audit of what its scores measure. Across six archived adapter-baseline comparisons, paired tests of pass@k at k = 1,…
Code Generation