Imagen de Portada

Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Bui, Nghi D. Q.
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Agentic Coding Needs Proactivity, Not Just Autonomy
por: Bui, Nghi D. Q., et al.
Publicado: (2026)

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
por: Phan, Huy Nhat, et al.
Publicado: (2024)

On the Impacts of Contexts on Repository-Level Code Generation
por: Hai, Nam Le, et al.
Publicado: (2024)

Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals
por: Nghiem, Khanh, et al.
Publicado: (2024)

Functional Overlap Reranking for Neural Code Generation
por: To, Hung Quoc, et al.
Publicado: (2023)

Dopamin: Transformer-based Comment Classifiers through Domain Post-Training and Multi-level Layer Aggregation
por: Hai, Nam Le, et al.
Publicado: (2024)

Effective Harness Engineering for Algorithm Discovery with Coding Agents
por: Ishibashi, Yoichi, et al.
Publicado: (2026)

RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion
por: Phan, Huy N., et al.
Publicado: (2024)

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
por: Nguyen, Minh Huynh, et al.
Publicado: (2024)

CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs
por: Bui, Nghi D. Q., et al.
Publicado: (2023)

Code as Agent Harness
por: Ning, Xuying, et al.
Publicado: (2026)

Coding Agents are Effective Long-Context Processors
por: Cao, Weili, et al.
Publicado: (2026)

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
por: Zhong, Hailin, et al.
Publicado: (2026)

Architectural Design Decisions in AI Agent Harnesses
por: Wei, Hu
Publicado: (2026)

SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
por: Zhu, Ningyan, et al.
Publicado: (2026)

In-Context Code-Text Learning for Bimodal Software Engineering
por: Tang, Xunzhu, et al.
Publicado: (2024)

AI-Assisted Code Review as a Scaffold for Code Quality and Self-Regulated Learning: An Experience Report
por: Oliveira, Eduardo, et al.
Publicado: (2026)

AIBuildAI: An AI Agent for Automatically Building AI Models
por: Zhang, Ruiyi, et al.
Publicado: (2026)

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
por: Chu, Zhaoyang, et al.
Publicado: (2026)

A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP
por: Yang, Xi, et al.
Publicado: (2026)

The Last Harness You'll Ever Build
por: Seong, Haebin, et al.
Publicado: (2026)

OAgents: An Empirical Study of Building Effective Agents
por: Zhu, He, et al.
Publicado: (2025)

XMainframe: A Large Language Model for Mainframe Modernization
por: Dau, Anh T. V., et al.
Publicado: (2024)

SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs
por: Pham, Minh V. T., et al.
Publicado: (2025)

Building Scaffolding Dialogue Data with LLM-Simulated Novices
por: Chen, Si, et al.
Publicado: (2025)

Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams
por: Agostino, Christopher J., et al.
Publicado: (2026)

Why Trust in AI May Be Inevitable
por: Truong, Nghi, et al.
Publicado: (2025)

Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
por: Cheng, Zihao, et al.
Publicado: (2026)

AI Agent for Reverse-Engineering Legacy Finite-Difference Code and Translating to Devito
por: Hou, Yinghan, et al.
Publicado: (2026)

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

Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of Biomechanics
por: Yan, Hanzhi, et al.
Publicado: (2025)

Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
por: Liu, Yuanzhe, et al.
Publicado: (2025)

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

How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework
por: uulu, Choro Ulan, et al.
Publicado: (2026)

Why They Disagree: Decoding Differences in Opinions about AI Risk on the Lex Fridman Podcast
por: Truong, Nghi, et al.
Publicado: (2025)

NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science
por: Zhou, Bing, et al.
Publicado: (2026)

SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling
por: Wang, Haoran, et al.
Publicado: (2025)

Exploring Effective Strategies for Building a User-Configured GPT for Coding Classroom Dialogues
por: Bai, Luwei, et al.
Publicado: (2025)

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
por: Wong, Sherman, et al.
Publicado: (2025)

Building Effective Safety Guardrails in AI Education Tools
por: Clark, Hannah-Beth, et al.
Publicado: (2025)