Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks
AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Envir…
Code GenerationBeyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs
Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance varies across programming languages, problem families, and failure mod…
Code GenerationRecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks
Reasoning-capable large language models can be induced to spend their generation budget on injected decoy tasks rather than answering the user's question, causing denial of service when no final answer is produced and de…
Question AnsweringCode GenerationCASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs
Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip …
Code GenerationMicroskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation
Large language models and AI coding agents have reshaped software development, but the path to fully AI-native systems faces structural challenges. Chief among them is managing context windows without losing accuracy or …
Code GenerationClosing the Loop on Latent Reasoning via Test-Time Reconstruction
Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottleneck. However, this shift also removes a …
Mathematical ReasoningAnswer GenerationCode GenerationMLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, exis…
Domain GeneralizationCode GenerationSePO: Self-Evolving Prompt Agent for System Prompt Optimization
System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt agent that refines task agents' system prom…
Code GenerationTENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts
Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the large static parameter footprint of experts. Existing compression appr…
Code GenerationA Practice Auditing Framework for Large Language Model Use: Collective Empiricism, Pseudo-Rational Cognition, and Governance of AI-Generated Content
Large language models are increasingly used for knowledge acquisition, code generation, academic writing, and agent-based automation. In these settings, users may obtain highly structured answers, plans, and judgments wi…
Code GenerationModuLoop : Low-Level Code Generation using Modular Synthesizer and Closed-Loop Debugger for Robotic Control
Large Language Models (LLMs) have demonstrated impressive performance across various domains, including code generation and problem solving. However, their application in robotic control, particularly in low-level tasks …
Code GenerationEvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes…
Reinforcement LearningMathematical ReasoningCode GenerationWhen Model Merging Breaks Routing: Training-Free Calibration for MoE
Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing merging techniques, largely based on linear parameter arithmetic or optimiz…
Mathematical ReasoningCode GenerationLearn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuni…
Reinforcement LearningCode GenerationThe Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation
Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cues, meaning contextual words or metadata outside the task specificatio…
Code GenerationDiagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition
Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordinate signatures, module paths, input-outp…
Code GenerationStepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon reasoning, multi-step dependencies, and strict correctness constraints in Verilog and VHDL. We present StepPRM-RTL, a …
Trajectory ModelingCode GenerationMPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics
To study the ability to infer physical dynamics from videos and extrapolate them forward in time, we assemble a dataset of 2D Material Point Method (MPM) physical simulations covering rich physical phenomena such as defo…
Physical SimulationsCode GenerationEstRTL: Functional Estimation Guided RTL Code Generation
Optimizing register transfer level (RTL) code is of vital importance in hardware design. Large language models (LLMs) provide new methods for the automatic generation and optimization of RTL code, offering the potential …
Code GenerationATLAS: Agentic Test-time Learning-to-Allocate Scaling
Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed…
Multimodal ReasoningQuestion AnsweringCode Generation