Live in the Loop: Rapid Run-time Feedback for Prompts
Toni Mattis, Abdullatif Ghajar, Tom Beckmann, Robert Hirschfeld
2026年份
2被引次数
摘要
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.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
相关 Paper
- How Beginning Programmers and Code LLMs (Mis)read Each OtherSydney Nguyen, Hannah McLean Babe, Yangtian Zi, Arjun Guha 等CHI 2024 · 被引用 66 次
- Fixing Large Language Models' Specification Misunderstanding for Better Code GenerationZhao Tian, Junjie Chen, Xiangyu ZhangICSE 2025 · 被引用 6 次
- Causality-Aided Evaluation and Explanation of Large Language Model-Based Code GenerationZhenlan Ji, Pingchuan Ma, Zongjie Li, Zhaoyu Wang 等ISSTA 2025 · 被引用 1 次
- Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt EngineeringTanghaoran Zhang, Yue Yu, Xinjun Mao, Shangwen Wang 等ICSE 2025 · 被引用 3 次
- CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language ProgrammingLi Feng, Ryan Yen, Yuzhe You, Mingming Fan 等CHI 2024 · 被引用 28 次
