Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
TaPR: Test-Aware Policy Refinement for Feedback-Conditioned Code Generation
Multi-turn code agents rely on execution feedback to repair incorrect programs, yet standard reinforcement learning paradigms optimize and evaluate policy performance primarily using single-shot outcome rewards. This mis…
Reinforcement LearningCode GenerationAdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several future tokens in parallel to enrich its s…
Mathematical ReasoningCode GenerationSAF-OPD: Stable Advantage Fusion for On-Policy Distillation
Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but ca…
Mathematical ReasoningReinforcement LearningCode GenerationVISA: A Structured Description Protocol for Agent-Based Simulation Models Towards Machine Reproducibility
Agent-based models (ABMs) are difficult to reproduce: their behavior is spread across prose narratives, platform-specific code, and implicit assumptions, so that two readers routinely reconstruct different models from th…
Code GenerationSpecification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models
Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies can lead to deadlocks. In such settings, protocol refinement - the safe substi…
Program SynthesisCode GenerationBeyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold
A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes. We argue that reinforcement learning (RL)-trained policies should…
Reinforcement LearningMathematical ReasoningInstruction FollowingCode GenerationPrintAnything: Learning an Intermediate Representation for 3D printing G-code Generation
Point clouds are one of the most fundamental and widely used 3D representations, serving as the most basic geometric representation of 3D shapes. Nevertheless, most existing 3D printing pipelines require a watertight mes…
Code GenerationPoint CloudsDrawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings
Recovering Parametric CAD sequences from raster-format 2D Computer-Aided Design (CAD) drawings accumulated prior to digital transformation is important for part reproduction and manufacturing process automation. However,…
Code GenerationLightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models
On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD supervision should also have generated the…
Mathematical ReasoningCode GenerationWhen Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences
Large language models (LLMs) are increasingly required to integrate multiple sources of information that may be inconsistent or conflicting. However, there is still a lack of controllable and attributable methods for ana…
Code GenerationThink Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control of physical AI systems. Yet, when deployed at the edge, the…
Multi-hop Question AnsweringArithmetic ReasoningCode GenerationFrom Interface to Inference: Eliciting Any-Order Inference from Any-Order Models
Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a process we call any-order inference. For autoregressive language model…
Code GenerationEvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural re…
Code GenerationOmniQEC: discovering practical quantum error-correcting codes by an AI scientist
Quantum error correction (QEC) is indispensable for scalable fault-tolerant quantum computing. However, discovering QEC codes that remain effective is challenging, as logical performance depends on the interplay between …
Code GenerationA Control System, a Dataset, and a Recipe for Making Frozen LLM Agents Learn a Domain
Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a planning strategy, and a verification policy. Two 2026 systems, Meta-H…
Reinforcement LearningCode GenerationSecDrift: Measuring Sector-Conditioned Security Drift in AI-Generated Code
LLMs are increasingly used for code generation in critical infrastructure, yet the security effect of domain-specific prompting is understudied. We present SecDrift, a benchmark measuring sector-conditioned security drif…
Code GenerationRIDGE: An Autonomous Framework for Validation and Method Discovery in LLM-Generated Option Pricing
Automated code generation is becoming an important tool in quantitative finance, where large language models can generate option pricing implementations directly from mathematical model specifications. Validating such im…
Code GenerationBeyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation
Repository-level code generation relies on heterogeneous evidence whose relevance, compatibility, and completeness are inherently uncertain. Similar-code examples, repository context, and project-specific APIs may provid…
Code GenerationPoster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored. Existing benchmarks often rely on explicitly specified security requ…
Code GenerationAn LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models
We present a structured large-language-model-driven workflow for automated multi-variable control design from dynamic process models. The workflow decomposes the design task into constrained code-generation steps: plant-…
Code GenerationPoint Tracking