paper-with-me

Papers Code Generation

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

Repo0: Design-Driven Zero-to-All Code Generation

2026-08-20 · Silin Chen, Haoyi Teng, Xiaodong Gu, Yuling Shi 외 arxiv

Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an…

Code Generation

Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning

2026-08-19 · Yajie Yin arxiv

Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors. Yet the verificati…

Medical DiagnosisCode Generation

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

2026-08-19 · Yanlun Tu, Huacan Wang, Ziyue Zhou, Jie Zhou 외 hf

Programmable logic controllers (PLCs) run industrial plants, and large language models can already generate independent program organization units (POUs) for them. Whether such logic integrates into an existing PLC proje…

Code Generation

LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection

2026-08-19 · Tu Anh Hoang Nguyen, Dang Nguyen, Thuc Duy Le, Trung Le 외 arxiv

Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing detectors rely on geometric or reconstruc…

Anomaly DetectionCode Generation

TokEval: A Tokenizer Evaluation Suite

2026-08-18 · Clara Meister arxiv

Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be partly attributed to a limited understanding of which t…

Mathematical ReasoningCode Generation

A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design

2026-08-18 · Huanshu Zhang, Kegeng Tang, Lei Kang, Sawyer D. Campbell 외 arxiv

Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulatio…

Code Generation

When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents

2026-08-17 · Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu 외 arxiv

Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text generation models into the co…

Text GenerationCode Generation

TDD-Agent: Test-Driven Reasoning for Code Generation

2026-08-17 · Hongyue Yu, Kefan Li, Jiakun Li, Hongzheng Chai 외 arxiv

Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static …

Code Generation

Remote-Sensing City Layout Extraction with MLLM

2026-08-17 · Zigan Zhou, Kai Li, Yupeng Deng arxiv

Remote-sensing systems usually describe urban content with detection boxes, semantic masks, or vector boundaries. Such outputs locate classes and support image-plane scoring, yet they do not by themselves constitute an e…

Code Generation

Competing at Every Price Point with Agentic Evolution over a Menu of LLMs

2026-08-17 · Andrew Borthwick arxiv

Consider a firm that surveys its competition for a particular agentic task and seeks to offer superior accuracy at every competitor price point. A firm that Pareto-dominated its competitors would leave no rational custom…

Code Generation

Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline

2026-08-17 · Mikhail Surikov arxiv

AI-assisted development tools generate vulnerable code at significant rates, yet few automated mechanisms exist to detect, enrich, fix, and verify security issues at development velocity, particularly ones that ground re…

Vulnerability DetectionCode Generation

Detecting Contaminated Code-Generation Prompt Batches via Influence Functions

2026-08-14 · Francesco Quinzan, Noor Munir, Yishun Lu, Stephen Roberts arxiv

Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Existing defenses typically rely on predefined threat models or known vu…

Code Generation

Agentic Transaction: Towards ACID-Compliant Agent Systems

2026-08-14 · Zhaoyan Sun, Xiaoxiao Wang, Guoliang Li arxiv

Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasoning, tool use, code generation, and workspace manipulation. As agents in…

Code Generation

Vero: Can AI Agents Build Formally Verified Software Repositories?

2026-08-13 · Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song 외 arxiv

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked pr…

Code Generation

Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ

2026-08-13 · Zongyun Zhang, Jiacheng Ruan, Xian Gao, Ruizhu Zhou 외 arxiv

Although multimodal large language models (MLLMs) have shown substantial potential in visual understanding and graphic code generation, editing scientific figures through code presents a greater challenge: a model must j…

Instruction FollowingVisual LocalizationCode Generation

StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems

2026-08-13 · Yanwen Peng, Delvin Ce Zhang, Xi Wang, Nikolaos Aletras arxiv

Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's continuous hidden states into discrete toke…

Question AnsweringCode Generation

Latent On-Policy Self-Distillation

2026-08-13 · Guibin Zhang, Jiayang Lyu, Ran Sun, Xinlei Yu 외 arxiv

Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-te…

Code Generation

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

2026-08-13 · Joào Pedro Monteiro Pereira, Vinicius Cardoso Garcia arxiv

In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-line phrases. We ask whether grounding those specifications in ISO/IEC 25010 Quality Model, either as rich natural-languag…

Code Generation

INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators

2026-08-11 · Rose Niousha, Minwoo Kang, Narges Norouzi arxiv

Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, where student simulation is increasingly used for various application…

Code Generation

Parameter Exploration for RLVR via Variational Learning

2026-08-10 · Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych hf

Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcement learning recipes that can significan…

Mathematical ReasoningReinforcement LearningCode Generation
← 이전 21–40 / 3,062 다음 →