Towards Machine-Generated Code for the Resolution of User Intentions

• URL: http://arxiv.org/abs/2504.17531v1
• Date: Thu, 24 Apr 2025 13:19:17 GMT
• Title: Towards Machine-Generated Code for the Resolution of User Intentions
• Authors: Justus Flerlage, Ilja Behnke, Odej Kao,
• Abstract summary: We investigate the feasibility of generating and collaborating through code generation that results from prompting an LLM with a concrete user intention.<n>We provide in-depth analysis and comparison of various user intentions, the resulting code, and its execution.<n>The employed LLM, GPT-4o-mini, exhibits remarkable proficiency in the generation of code-oriented in accordance with provided user intentions.
• Score: 2.762180345826837
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The growing capabilities of Artificial Intelligence (AI), particularly Large Language Models (LLMs), prompt a reassessment of the interaction mechanisms between users and their devices. Currently, users are required to use a set of high-level applications to achieve their desired results. However, the advent of AI may signal a shift in this regard, as its capabilities have generated novel prospects for user-provided intent resolution through the deployment of model-generated code, which is tantamount to the generation of workflows comprising a multitude of interdependent steps. This development represents a significant progression in the realm of hybrid workflows, where human and artificial intelligence collaborate to address user intentions, with the former responsible for defining these intentions and the latter for implementing the solutions to address them. In this paper, we investigate the feasibility of generating and executing workflows through code generation that results from prompting an LLM with a concrete user intention, such as \emph{Please send my car title to my insurance company}, and a simplified application programming interface for a GUI-less operating system. We provide in-depth analysis and comparison of various user intentions, the resulting code, and its execution. The findings demonstrate a general feasibility of our approach and that the employed LLM, GPT-4o-mini, exhibits remarkable proficiency in the generation of code-oriented workflows in accordance with provided user intentions.

Related papers

• Interactive Agents to Overcome Ambiguity in Software Engineering [61.40183840499932]
  AI agents are increasingly being deployed to automate tasks, often based on ambiguous and underspecified user instructions.<n>Making unwarranted assumptions and failing to ask clarifying questions can lead to suboptimal outcomes.<n>We study the ability of LLM agents to handle ambiguous instructions in interactive code generation settings by evaluating proprietary and open-weight models on their performance.
  arXiv  Detail & Related papers  (2025-02-18T17:12:26Z)
• Large Action Models: From Inception to Implementation [51.81485642442344]
  Large Action Models (LAMs) are designed for action generation and execution within dynamic environments. LAMs hold the potential to transform AI from passive language understanding to active task completion. We present a comprehensive framework for developing LAMs, offering a systematic approach to their creation, from inception to deployment.
  arXiv  Detail & Related papers  (2024-12-13T11:19:56Z)
• Survey of User Interface Design and Interaction Techniques in Generative AI Applications [79.55963742878684]
  We aim to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. We also strive to lower the entry barrier for those attempting to learn more about the design of generative AI applications.
  arXiv  Detail & Related papers  (2024-10-28T23:10:06Z)
• Data Analysis in the Era of Generative AI [56.44807642944589]
  This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow. We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps.
  arXiv  Detail & Related papers  (2024-09-27T06:31:03Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)
• Constraining Participation: Affordances of Feedback Features in Interfaces to Large Language Models [49.74265453289855]
  Large language models (LLMs) are now accessible to anyone with a computer, a web browser, and an internet connection via browser-based interfaces. This paper examines the affordances of interactive feedback features in ChatGPT's interface, analysing how they shape user input and participation in iteration.
  arXiv  Detail & Related papers  (2024-08-27T13:50:37Z)
• Empowering Agile-Based Generative Software Development through Human-AI Teamwork [24.743864861980803]
  We propose AgileGen, an agile-based generative software development through human-AI teamwork. A memory pool mechanism is used to collect user decision-making scenarios and recommend them to new users.
  arXiv  Detail & Related papers  (2024-07-22T11:54:44Z)
• Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [110.25679611755962]
  Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. We introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. We empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals.
  arXiv  Detail & Related papers  (2024-02-14T14:36:30Z)
• Leveraging Large Language Models to Build and Execute Computational Workflows [40.572754656757475]
  This paper explores how these emerging capabilities can be harnessed to facilitate complex scientific research. We present initial findings from our attempt to integrate Phyloflow with OpenAI's function-calling API, and outline a strategy for developing a comprehensive workflow management system.
  arXiv  Detail & Related papers  (2023-12-12T20:17:13Z)
• User Friendly and Adaptable Discriminative AI: Using the Lessons from the Success of LLMs and Image Generation Models [0.6926105253992517]
  We develop a new system architecture that enables users to work with discriminative models. Our approach has implications on improving trust, user-friendliness, and adaptability of these versatile but traditional prediction models.
  arXiv  Detail & Related papers  (2023-12-11T20:37:58Z)
• Demystifying a Dark Art: Understanding Real-World Machine Learning Model Development [2.422369741135428]
  We analyze over 475k user-generated on OpenML, an open-source platform for tracking and sharing machine learning. We find that users often adopt a manual, automated, or mixed approach when iterating on their iterations.
  arXiv  Detail & Related papers  (2020-05-04T14:33:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.