Live in the Loop: Rapid Run-time Feedback for Prompts
Toni Mattis, Abdullatif Ghajar, Tom Beckmann, Robert Hirschfeld
2026Year
2Citations
Abstract
Programmers formulate prompts for code generation based on their understandings of problem domain and LLM ability to execute instructions. A deficiency in either understanding yields inadequate generated code, requiring programmers to revise their understandings based on deficiencies observed in the generated code.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 9076819c-8dd5-4ad9-b038-eabd4ad8a20eRelated papers
- How Beginning Programmers and Code LLMs (Mis)read Each OtherSydney Nguyen, Hannah McLean Babe, Yangtian Zi, Arjun Guha et al.CHI 2024 · 66 citations
- Fixing Large Language Models' Specification Misunderstanding for Better Code GenerationZhao Tian, Junjie Chen, Xiangyu ZhangICSE 2025 · 6 citations
- Causality-Aided Evaluation and Explanation of Large Language Model-Based Code GenerationZhenlan Ji, Pingchuan Ma, Zongjie Li, Zhaoyu Wang et al.ISSTA 2025 · 1 citation
- Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt EngineeringTanghaoran Zhang, Yue Yu, Xinjun Mao, Shangwen Wang et al.ICSE 2025 · 3 citations
- CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language ProgrammingLi Feng, Ryan Yen, Yuzhe You, Mingming Fan et al.CHI 2024 · 28 citations
