Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels.…
Mathematical ReasoningCode GenerationQuestioning the Questions: Sustaining Self-Evolution in Reasoning Models
Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigate why performance deteriorates over successive rounds and …
Mathematical ReasoningCode Generation4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics programs. To accomplish this, agents must translate visu…
Physical SimulationsCode GenerationCARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning
Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasoning and code generation. In practical systems, howev…
Mathematical ReasoningReinforcement LearningCode GenerationSmaller Models, Better Rejects: Preference Distillation Scaling
Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated failures are the most informative negatives and that rejects must come…
Knowledge DistillationMathematical ReasoningCode GenerationQuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code
Large language models are strong general-purpose code generators, but executable algorithmic trading remains a demanding specialization target: a model must translate a natural-language strategy specification into correc…
Instruction FollowingCode GenerationDating the Model: Hidden Dates in System Prompts Affect LLM Evaluation
Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection of the current date into system prompts,…
Machine TranslationCode GenerationCorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advantages by centering and normalizing rewards across rollouts of the same prompt. For multiple rewards, GRP…
Code GenerationPrincipled Thoughts for Latent Recursive LLM Systems
Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supervises only the Cross-Entropy (CE) of th…
Code GenerationROSS: Relearning from Self-Generated Rollouts through Selective Supervision
Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience is often treated as stale once the policy advances. Historical rollouts …
Reinforcement LearningInstruction FollowingCode GenerationDuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation
On-policy distillation (OPD) trains a student on its own responses with token-level feedback from a stronger teacher, yet the teacher can fail on questions the student already answers correctly, and how often each model …
Instruction FollowingCode GenerationCapable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple cus…
Code GenerationRegister Tokens for Bounded-State Reasoning in Diffusion Language Models
Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across generation chunks normally requires keeping earlier generated text in…
Reinforcement LearningCode GenerationRetrofitting Code Using LLMs to Support Exceptional Behavior
Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of software systems, allowing developers to det…
Code GenerationΦ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing the very infrastructure that powers them. …
Code GenerationRISE: Recursive Improvement via Self-Extrapolating Policy Distillation
On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while se…
Mathematical ReasoningCode GenerationSubstrate-Aware AI Agents: Execution Context as a First-Class Input
Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine what counts as a suitable plan. We call the absence of this execution…
Code GenerationAutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems
Improving an industrial recommender is an iterative research-and-engineering process rather than a direct path from idea to deployment. In \textbf{DASHEN, NetEase's gaming-community app}, algorithm engineers typically id…
Code GenerationBeyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
AI coding systems are moving from autocomplete and chat toward agents that can inspect repositories, edit multiple files, run tools, write tests, open pull requests, and work for long periods with limited supervision. Th…
Code GenerationDynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
LLM-based code generation fails when correctness depends on execution-dependent coupling: the meaning of one routine is defined by the runtime behavior of another, a relationship that cannot be resolved from textual desc…
Code Generation