Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iteration…
Code GenerationStrategic Over-Parameterization for Generalizable Low-Rank Adaptation
Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impractical due to its computational and memory demands. Parameter-efficient fine-tuning (PEFT) approaches such as Low-Rank A…
parameter-efficient fine-tuningArithmetic ReasoningCode GenerationGenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design
Genetic circuit design remains a laborious, expert-driven process despite decades of progress in synthetic biology. We study this problem through code generation: models produce Python code in pysbol3 to construct geneti…
Reinforcement LearningCode GenerationCode RepairHydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support
Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness checks such as unit tests. Existing solutions for repairing static erro…
Code GenerationChronoAgentic: A Code-based Multi-Agent World Simulator for Physically Grounded Simulation Construction
Video-based world models generate visually plausible rollouts, but since they infer dynamics in latent states, they enforce no explicit physical constraints: contacts drift, shapes distort, and motion loses consistency. …
Code GenerationTest-Time Learning with an Evolving Library
We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of ada…
Mathematical ReasoningCode GenerationWhen Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Objectives: We study whether temporally stale repository snippets act as…
Code GenerationCode CompletionLearning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewa…
Reinforcement LearningMathematical ReasoningCode GenerationLearning from Language Feedback via Variational Policy Distillation
Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address…
Reinforcement LearningMathematical ReasoningCode GenerationGRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critical paradigm. Recent RL-based post-training has increasingly split into…
Reinforcement LearningMathematical ReasoningCode GenerationChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation
Existing API-based agentic systems for RTL code generation are fundamentally misaligned with industrial practice: they assume a golden testbench is available at generation time, rely on closed-source APIs incompatible wi…
Reinforcement LearningCode GenerationAI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability.…
Code GenerationTRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
Deploying language models as autonomous agents requires more than per-task accuracy: when an agent faces a queue of problems under a finite token budget, it must decide which to attempt, in what order, and how much compu…
Code GenerationHLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning
High-Level Synthesis (HLS) compiles algorithmic C/C++ descriptions into hardware, with Quality of Results (QoR)---latency and resource utilization---critically governed by pragma configurations and code structure. Existi…
Reinforcement LearningCode GenerationTurning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent
Today's agents are highly effective at implementing well-scoped software design plans, but user intent is often vague and admits multiple equally valid solutions. In this paper, we introduce SpecBench, a new benchmark fo…
Code GenerationBeyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call tr…
Mathematical ReasoningCode GenerationSkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strate…
Mathematical ReasoningQuestion AnsweringCode GenerationDecision MakingStepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCode…
Reinforcement LearningCode GenerationMulti-Token Residual Prediction
Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of to…
Code GenerationUncertainty Quantification for LLM-based Code Generation
Prediction sets provide a theoretically grounded framework for quantifying uncertainty in machine learning models. Adapting them to structured generation tasks, in particular, large language model (LLM) based code genera…
Code Generation