Imagen de Portada

Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Chengran, Sun, Zhensu, Kang, Hong Jin, Shi, Jieke, Lo, David
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
por: Yang, Chengran, et al.
Publicado: (2024)

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
por: Sun, Zhensu, et al.
Publicado: (2025)

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
por: Sun, Zhensu, et al.
Publicado: (2025)

Greening Large Language Models of Code
por: Shi, Jieke, et al.
Publicado: (2023)

Ecosystem of Large Language Models for Code
por: Yang, Zhou, et al.
Publicado: (2024)

Compiling Code LLMs into Lightweight Executables
por: Shi, Jieke, et al.
Publicado: (2026)

Executing as You Generate: Hiding Execution Latency in LLM Code Generation
por: Sun, Zhensu, et al.
Publicado: (2026)

Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead
por: Shi, Jieke, et al.
Publicado: (2024)

Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
por: Yang, Chengran, et al.
Publicado: (2026)

Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
por: Yang, Zhou, et al.
Publicado: (2024)

Curiosity-Driven Testing for Sequential Decision-Making Process
por: He, Junda, et al.
Publicado: (2025)

AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
por: Lyu, Yunbo, et al.
Publicado: (2026)

LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis
por: Tan, Gou, et al.
Publicado: (2026)

The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget
por: Pan, Dangfeng, et al.
Publicado: (2025)

Unveiling Memorization in Code Models
por: Yang, Zhou, et al.
Publicado: (2023)

AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
por: Sun, Zhensu, et al.
Publicado: (2024)

Mut4All: Fuzzing Compilers via LLM-Synthesized Mutators Learned from Bug Reports
por: Wang, Bo, et al.
Publicado: (2025)

PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing
por: Huang, Huihui, et al.
Publicado: (2026)

Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies
por: Shi, Jieke, et al.
Publicado: (2024)

FDI: Attack Neural Code Generation Systems through User Feedback Channel
por: Sun, Zhensu, et al.
Publicado: (2024)

From Code to Courtroom: LLMs as the New Software Judges
por: He, Junda, et al.
Publicado: (2025)

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
por: Sun, Zhensu, et al.
Publicado: (2022)

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models
por: Yang, Zhou, et al.
Publicado: (2023)

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
por: Shi, Yuling, et al.
Publicado: (2026)

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
por: Yang, Chengran, et al.
Publicado: (2025)

Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
por: Hu, Li, et al.
Publicado: (2026)

Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis
por: Huang, Huihui, et al.
Publicado: (2026)

"My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants
por: Lyu, Yunbo, et al.
Publicado: (2025)

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
por: Li, Yikun, et al.
Publicado: (2026)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
por: Chen, Zhi, et al.
Publicado: (2026)

From Noise to Knowledge: Interactive Summaries for Developer Alerts
por: Yetiştiren, Burak, et al.
Publicado: (2025)

An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
por: Li, Yikun, et al.
Publicado: (2026)

TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning
por: Wang, Guoqing, et al.
Publicado: (2026)

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs
por: Shi, Jieke, et al.
Publicado: (2024)

Harnessing Hype to Teach Empirical Thinking: An Experience With AI Coding Assistants
por: Wyrich, Marvin, et al.
Publicado: (2026)

What You Trust Is Insecure: Demystifying How Developers (Mis)Use Trusted Execution Environments in Practice
por: Niu, Yuqing, et al.
Publicado: (2025)

SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents
por: Chang, Jianming, et al.
Publicado: (2025)

Hotfixing Large Language Models for Code
por: Yang, Zhou, et al.
Publicado: (2024)

LLM-as-a-Judge for Software Engineering: Literature Review, Vision, and the Road Ahead
por: He, Junda, et al.
Publicado: (2025)

A Study on Thinking Patterns of Large Reasoning Models in Code Generation
por: Halim, Kevin, et al.
Publicado: (2025)