# Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals

arXiv: https://arxiv.org/abs/2403.14592 · HTML: https://mlsanity.com/paper/2403.14592/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 8 of 8)

- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment](https://mlsanity.com/paper/2309.14049/) (2023)
- [Investigating and Designing for Trust in AI-powered Code Generation Tools](https://mlsanity.com/paper/2305.11248/) (2023)
- [Large Language Models of Code Fail at Completing Code with Potential Bugs](https://mlsanity.com/paper/2306.03438/) (2023)
- [Unsupervised Evaluation of Code LLMs with Round-Trip Correctness](https://mlsanity.com/paper/2402.08699/) (2024)
- [The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation](https://mlsanity.com/paper/2305.06156/) (2023)
- [Better Language Models of Code through Self-Improvement](https://mlsanity.com/paper/2304.01228/) (2023)

## Built on by (most cited first, 2 of 2)

- [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://mlsanity.com/paper/2512.04111/) (2025)
- [Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency](https://mlsanity.com/paper/2504.15989/) (2025)

## Abstract (arXiv)

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.