Imagen de Portada

Stingy Context: 18:1 Hierarchical Code Compression for LLM Auto-Coding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Ostby, David Linus
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
por: Jiang, Hongchao, et al.
Publicado: (2025)

AutoCode: LLMs as Problem Setters for Competitive Programming
por: Zhou, Shang, et al.
Publicado: (2025)

Towards an Understanding of Context Utilization in Code Intelligence
por: Wang, Yanlin, et al.
Publicado: (2025)

Scaling Granite Code Models to 128K Context
por: Stallone, Matt, et al.
Publicado: (2024)

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
por: Shi, Yuling, et al.
Publicado: (2024)

Verification Limits Code LLM Training
por: Gureja, Srishti, et al.
Publicado: (2025)

UA-Code-Bench: A Competitive Programming Benchmark for Evaluating LLM Code Generation in Ukrainian
por: Syromiatnikov, Mykyta, et al.
Publicado: (2025)

Pragmatic Reasoning improves LLM Code Generation
por: Cao, Zhuchen, et al.
Publicado: (2025)

Crystal: Illuminating LLM Abilities on Language and Code
por: Tao, Tianhua, et al.
Publicado: (2024)

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
por: Peng, Yun, et al.
Publicado: (2024)

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents
por: Zhu, Ming, et al.
Publicado: (2024)

YABLoCo: Yet Another Benchmark for Long Context Code Generation
por: Valeev, Aidar, et al.
Publicado: (2025)

LocAgent: Graph-Guided LLM Agents for Code Localization
por: Chen, Zhaoling, et al.
Publicado: (2025)

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
por: Zhang, Ziyao, et al.
Publicado: (2024)

Collaboration is all you need: LLM Assisted Safe Code Translation
por: Karanjai, Rabimba, et al.
Publicado: (2025)

Issue Localization via LLM-Driven Iterative Code Graph Searching
por: Jiang, Zhonghao, et al.
Publicado: (2025)

EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories
por: Li, Jia, et al.
Publicado: (2024)

Demo-Craft: Using In-Context Learning to Improve Code Generation in Large Language Models
por: Kapu, Nirmal Joshua, et al.
Publicado: (2024)

IndustryCode: A Benchmark for Industry Code Generation
por: Zeng, Puyu, et al.
Publicado: (2026)

Rethinking Code Refinement: Learning to Judge Code Efficiency
por: Seo, Minju, et al.
Publicado: (2024)

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
por: Zheng, Tianyu, et al.
Publicado: (2024)

CodeMirage: Hallucinations in Code Generated by Large Language Models
por: Agarwal, Vibhor, et al.
Publicado: (2024)

A Code Comprehension Benchmark for Large Language Models for Code
por: Havare, Jayant, et al.
Publicado: (2025)

Granite Code Models: A Family of Open Foundation Models for Code Intelligence
por: Mishra, Mayank, et al.
Publicado: (2024)

CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
por: Sutawika, Lintang, et al.
Publicado: (2026)

CodeS: Natural Language to Code Repository via Multi-Layer Sketch
por: Zan, Daoguang, et al.
Publicado: (2024)

Testing the Effect of Code Documentation on Large Language Model Code Understanding
por: Macke, William, et al.
Publicado: (2024)

CodeNav: Beyond tool-use to using real-world codebases with LLM agents
por: Gupta, Tanmay, et al.
Publicado: (2024)

Let the Code LLM Edit Itself When You Edit the Code
por: He, Zhenyu, et al.
Publicado: (2024)

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
por: Zhuo, Terry Yue, et al.
Publicado: (2024)

MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks
por: Chervyakov, Artem, et al.
Publicado: (2025)

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
por: Jiang, Xue, et al.
Publicado: (2025)

CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
por: Su, Zian, et al.
Publicado: (2024)

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
por: Han, Hojae, et al.
Publicado: (2025)

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
por: Wang, Hanbin, et al.
Publicado: (2025)

Code2Doc: A Quality-First Curated Dataset for Code Documentation
por: Karaman, Recep Kaan, et al.
Publicado: (2025)

CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells
por: Naik, Atharva, et al.
Publicado: (2024)

Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
por: Sapkota, Ranjan, et al.
Publicado: (2025)

ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models
por: Han, Hojae, et al.
Publicado: (2024)

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
por: Zhuo, Terry Yue, et al.
Publicado: (2025)