Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs

• URL: http://arxiv.org/abs/2504.20406v1
• Date: Tue, 29 Apr 2025 04:03:37 GMT
• Title: Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
• Authors: Paiheng Xu, Gang Wu, Xiang Chen, Tong Yu, Chang Xiao, Franck Dernoncourt, Tianyi Zhou, Wei Ai, Viswanathan Swaminathan,
• Abstract summary: We propose an offline simulation framework to curate a software-specific skillset, a collection of verified scripts.<n>Our framework comprises two components: (1) task creation, using top-down functionality and bottom-up API synergy exploration to generate helpful tasks.<n> Experiments with Adobe Illustrator demonstrate that our framework significantly improves automation success rates, reduces response time, and saves runtime token costs.
• Score: 63.10710876536337
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming expertise and familiarity with specific APIs, posing barriers for many users. While Large Language Models (LLMs) can generate code from natural language queries, runtime code generation is severely limited due to unverified code, security risks, longer response times, and higher computational costs. To bridge the gap, we propose an offline simulation framework to curate a software-specific skillset, a collection of verified scripts, by exploiting LLMs and publicly available scripting guides. Our framework comprises two components: (1) task creation, using top-down functionality guidance and bottom-up API synergy exploration to generate helpful tasks; and (2) skill generation with trials, refining and validating scripts based on execution feedback. To efficiently navigate the extensive API landscape, we introduce a Graph Neural Network (GNN)-based link prediction model to capture API synergy, enabling the generation of skills involving underutilized APIs and expanding the skillset's diversity. Experiments with Adobe Illustrator demonstrate that our framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation. This is the first attempt to use software scripting interfaces as a testbed for LLM-based systems, highlighting the advantages of leveraging execution feedback in a controlled environment and offering valuable insights into aligning AI capabilities with user needs in specialized software domains.

Related papers

• API Agents vs. GUI Agents: Divergence and Convergence [35.28490346033735]
  API- and GUI-based large language models (LLMs) interact with graphical user interfaces in a human-like manner.<n>This paper systematically analyzes their divergence and potential convergence.<n>We indicate that continuing innovations in LLM-based automation are poised to blur the lines between API- and GUI-driven agents.
  arXiv  Detail & Related papers  (2025-03-14T04:26:21Z)
• Control Industrial Automation System with Large Language Models [2.2369578015657954]
  This paper introduces a framework for integrating large language models with industrial automation systems. At the core of the framework are an agent system designed for industrial tasks, a structured prompting method, and an event-driven information modeling mechanism. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets.
  arXiv  Detail & Related papers  (2024-09-26T16:19:37Z)
• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? [73.81908518992161]
  We introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering. Spider2-V features real-world tasks in authentic computer environments and incorporating 20 enterprise-level professional applications. These tasks evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems.
  arXiv  Detail & Related papers  (2024-07-15T17:54:37Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks [93.85005277463802]
  VisualWebArena is a benchmark designed to assess the performance of multimodal web agents on realistic tasks. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives.
  arXiv  Detail & Related papers  (2024-01-24T18:35:21Z)
• Lessons from Building StackSpot AI: A Contextualized AI Coding Assistant [2.268415020650315]
  A new breed of tools, built atop Large Language Models, is emerging. These tools aim to mitigate drawbacks by employing techniques like fine-tuning or enriching user prompts with contextualized information.
  arXiv  Detail & Related papers  (2023-11-30T10:51:26Z)
• TaskWeaver: A Code-First Agent Framework [50.99683051759488]
  TaskWeaver is a code-first framework for building LLM-powered autonomous agents. It converts user requests into executable code and treats user-defined plugins as callable functions. It provides support for rich data structures, flexible plugin usage, and dynamic plugin selection.
  arXiv  Detail & Related papers  (2023-11-29T11:23:42Z)
• Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API [17.991044940694778]
  We build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automation executor. To facilitate the exploitation of image-to-text pretrained knowledge, we follow the pixel-to-sequence paradigm. Our proposed reinforced UI instruction grounding model outperforms the state-of-the-art methods by a clear margin.
  arXiv  Detail & Related papers  (2023-10-07T07:22:41Z)
• AskIt: Unified Programming Interface for Programming with Large Language Models [0.0]
  Large Language Models (LLMs) exhibit a unique phenomenon known as emergent abilities, demonstrating adeptness across numerous tasks. This paper introduces AskIt, a domain-specific language specifically designed for LLMs. Across 50 tasks, AskIt generated concise prompts, achieving a 16.14 % reduction in prompt length compared to benchmarks.
  arXiv  Detail & Related papers  (2023-08-29T21:44:27Z)
• Low-code LLM: Graphical User Interface over Large Language Models [115.08718239772107]
  This paper introduces a novel human-LLM interaction framework, Low-code LLM. It incorporates six types of simple low-code visual programming interactions to achieve more controllable and stable responses. We highlight three advantages of the low-code LLM: user-friendly interaction, controllable generation, and wide applicability.
  arXiv  Detail & Related papers  (2023-04-17T09:27:40Z)

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.