Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals (2403.14592v1)

Published 21 Mar 2024 in cs.SE, cs.AI, and cs.HC

Abstract: As a research-product hybrid group in AI for Software Engineering (AI4SE), we present four key takeaways from our experience developing in-IDE AI coding assistants. AI coding assistants should set clear expectations for usage, integrate with advanced IDE capabilities and existing extensions, use extendable backend designs, and collect app data responsibly for downstream analyses. We propose open questions and challenges that academia and industry should address to realize the vision of next-generation AI coding assistants.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (17)
  1. Meta AI. 2024. Code Llama: Open Foundation Models for Code. arXiv:2308.12950 [cs.CL]
  2. Unsupervised Evaluation of Code LLMs with Round-Trip Correctness. arXiv:2402.08699 [cs.SE]
  3. Large Language Models of Code Fail at Completing Code with Potential Bugs. arXiv:2306.03438 [cs.LG]
  4. Large Language Models for Software Engineering: Survey and Open Problems. arXiv:2310.03533 [cs.SE]
  5. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv:2310.06770 [cs.CL]
  6. How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment. arXiv:2309.14049 [cs.HC]
  7. The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation. arXiv:2305.06156 [cs.CL]
  8. OpenAI. 2023. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]
  9. Communicative Agents for Software Development. arXiv:2307.07924 [cs.SE]
  10. The Programmer’s Assistant: Conversational Interaction with a Large Language Model for Software Development. In Proceedings of the 28th International Conference on Intelligent User Interfaces (IUI ’23). ACM. https://doi.org/10.1145/3581641.3584037
  11. What is it like to program with artificial intelligence? arXiv:2208.06213 [cs.HC]
  12. Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies. arXiv:2309.13063 [cs.IR]
  13. Selective Annotation Makes Language Models Better Few-Shot Learners. arXiv:2209.01975 [cs.CL]
  14. Gemini Team. 2023. Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL]
  15. Better Language Models of Code through Self-Improvement. arXiv:2304.01228 [cs.CL]
  16. Investigating and Designing for Trust in AI-powered Code Generation Tools. arXiv:2305.11248 [cs.HC]
  17. On the Concerns of Developers When Using GitHub Copilot. arXiv:2311.01020 [cs.SE]
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Khanh Nghiem (2 papers)
  2. Anh Minh Nguyen (2 papers)
  3. Nghi D. Q. Bui (30 papers)
Citations (1)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com