Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
AnCoder: Anchored Code Generation via Discrete Diffusion Models
Diffusion language models offer a compelling alternative to autoregressive code generation, enabling global planning and iterative refinement of complex program logic. However, existing approaches fail to respect the rig…
Code GenerationVeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation
Rapid advances in language models (LMs) have created new opportunities for automated code generation while complicating trade-offs between model characteristics and prompt design choices. In this work, we provide an empi…
Prompt EngineeringCode GenerationGradually Compacting Large Language Models for Reasoning Like a Boiling Frog
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources. To reduce resource consumption and accelerate inference, it …
Reinforcement LearningMathematical ReasoningCode GenerationProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas
Large language models (LLMs) have revolutionized automated code generation, yet the evaluation of their real-world effectiveness remains limited by static benchmarks and simplistic metrics. We present ProxyWar, a novel f…
Code GenerationCode RepairBeyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
Policy optimization methods like Group Relative Policy Optimization (GRPO) and its variants have achieved strong results on mathematical reasoning and code generation tasks. Despite extensive exploration of reward proces…
Mathematical ReasoningCode GenerationHierarchical Embedding Fusion for Retrieval-Augmented Code Generation
Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embed…
Code GenerationCode CompletionLLM-Assisted Replication for Quantitative Social Science
The replication crisis, the failure of scientific claims to be validated by further research, is one of the most pressing issues for empirical research. This is partly an incentive problem: replication is costly and less…
Code GenerationCodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by t…
Reinforcement LearningCode GenerationLearning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
Low-Rank Adaptation (LoRA) is the prevailing approach for efficient large language model (LLM) fine-tuning. Building on this paradigm, recent studies have proposed alternative initialization strategies, architectural mod…
Mathematical ReasoningInstruction FollowingCode GenerationLLM-FSM: Scaling Large Language Models for Finite-State Reasoning in RTL Code Generation
Finite-state reasoning, the ability to understand and implement state-dependent behavior, is central to hardware design. In this paper, we present LLM-FSM, a benchmark that evaluates how well large language models (LLMs)…
Code GenerationOne Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis
Large language models have recently surpassed specialized systems on code generation, yet their effectiveness on other code-analysis tasks remains less clear. At the same time, multi-task learning offers a way to unify d…
parameter-efficient fine-tuningMulti-Task LearningCode GenerationCan LLMs Do Rocket Science? Exploring the Limits of Complex Reasoning with GTOC 12
Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation and general reasoning, yet their capacity for autonomous multi-stage planning in high-dimensional, physically constrained environme…
Code GenerationEfficient Estimation of Kernel Surrogate Models for Task Attribution
Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text prediction -- simultaneously. A key question is how to quantify the influence …
Mathematical ReasoningReinforcement LearningCode GenerationBridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
Recently, there have been significant research interests in training large language models (LLMs) with reinforcement learning (RL) on real-world tasks, such as multi-turn code generation. While online RL tends to perform…
Reinforcement LearningCode GenerationOffline RLAntidistillation Fingerprinting
Model distillation enables efficient emulation of frontier large language models (LLMs), creating a need for robust mechanisms to detect when a third-party student model has trained on a teacher model's outputs. However,…
Mathematical ReasoningCode GenerationOpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
Solving diverse partial differential equations (PDEs) is fundamental in science and engineering. Large language models (LLMs) have demonstrated strong capabilities in code generation, symbolic reasoning, and tool use, bu…
Code GenerationGenerative Visual Code Mobile World Models
Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and inference-time. However, current approaches face a critical trade-off: text-based W…
Code GenerationLaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning
Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the …
Reinforcement LearningCode GenerationProbability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while tok…
Mathematical ReasoningCode GenerationPrism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs…
Mathematical ReasoningCode Generation