paper-with-me

Papers Code Generation

“Code Generation” 태그가 달린 논문 3,062편 · 필터 해제

Retrofitting Code Using LLMs to Support Exceptional Behavior

2026-09-09 · Linghan Zhong, Jiyang Zhang, Jayanth Srinivasa, Junyi Jessy Li 외 arxiv

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 Generation

Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?

2026-09-09 · Leilei Ding, Shumin Wang, Yuting Huang, Fanqi Wan 외 arxiv

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 Generation

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

2026-09-04 · Yang Li, Semih Yavuz, Shafiq Joty arxiv

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 Generation

Substrate-Aware AI Agents: Execution Context as a First-Class Input

2026-09-04 · Manu Agrawal arxiv

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 Generation

AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems

2026-09-04 · Qi Zhang, Yanlin Chen, Wenchao Xiao arxiv

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 Generation

Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle

2026-09-04 · Happy Bhati arxiv

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 Generation

Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics

2026-09-03 · Gnaneswar Villuri, Hashmath Shaik, Alex Doboli arxiv

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

Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One

2026-09-03 · Fred Zhangzhi Peng, Kaiwen Zheng, Anru R. Zhang arxiv

Language generation is almost universally treated as a sequential process: autoregressive models emit one token at a time, while diffusion language models replace token-level seriality with a long trajectory of iterative…

Code Generation

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation

2026-09-02 · Yunhao Liu, Hong Phuc Pham, Jaehong Yoon hf

Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated rep…

Code Generation

ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval

2026-09-01 · Aaryan Kapoor, Md Abdullah Al Hafiz Khan hf

Embedding-based code retrieval is a core component of coding agents and retrieval-augmented code generation, where retrieving correct code matters more than retrieving lexically similar code. Existing code-retrieval benc…

Code Generation

Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text

2026-08-31 · Minkyung Cho, Jihyo Kim, SeungWoo Song, Junghun Yuk 외 arxiv

Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from…

Code Generation

DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging

2026-08-28 · Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian arxiv

Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the …

Mathematical ReasoningInstruction FollowingCode Generation

Rubric-to-Code Credit Assignment for Reinforcement Learning

2026-08-28 · Rui Jin, Jikai Chen, Yihan Chen, Hao Zhou 외 arxiv

Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unlike conventional code generation, application quality depends on multiple…

Reinforcement LearningCode Generation

ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

2026-08-26 · Somgyuan Li, Ahmed M. Abdelmoniem, Shiqiang Wang arxiv

Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operatin…

Mathematical ReasoningQuestion AnsweringCode Generation

MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

2026-08-26 · Miseon Yu, Jaehoon Choi, Younghan Lee, Yunheung Paek arxiv

Despite their strong ability to generate code, large language models often fail to produce secure code, as their outputs frequently contain security vulnerabilities. Secure code generation is inherently challenging becau…

Code Generation

Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation

2026-08-25 · Tianyi Xiong, Zhengyuan Yang, Xiaofei Wang, Chung-Ching Lin 외 hf

Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identify a fundamental obstacle, termed visual repair coupling: a local code…

Code Generation

Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline

2026-08-24 · Eugenia Moris, José Ignacio Orlando arxiv

Developing competitive deep learning baselines for medical imaging remains a highly iterative process requiring literature review, implementation, experimentation, and expert refinement. Existing automation approaches ty…

Domain GeneralizationCode Generation

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

2026-08-24 · Xiao Zhang, Qumeng Sun, Jihao Li, Yiming Ren 외 arxiv

Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy strict end-to-end verification. Yet succes…

Mathematical ReasoningCode Generation

MARS: Multi-Specialist LLM Relay System for Competitive Programming

2026-08-24 · Andrei Mikhailov, Mikhail Burtsev, Alsu Sagirova hf

Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate t…

Code Generation

TESTNAV: Pareto-Guided Search for Compositional Robustness Testing

2026-08-20 · Arooj Arif, Tobias Hartung, Elena Botoeva, Alexandros Koliousis arxiv

Deep learning models remain vulnerable to real-world input perturbations, especially when multiple corruptions co-occur in the same input (e.g., brightness shifts and motion blur). Compositional testing reveals these int…

Code Generation
1–20 / 3,062 다음 →