LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study

• URL: http://arxiv.org/abs/2603.21439v4
• Date: Mon, 30 Mar 2026 13:59:16 GMT
• Title: LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study
• Abstract summary: Multidisciplinary Software Development (MSD) requires domain experts and developers to collaborate across incompatible formalisms and separate artifact sets.<n>We evaluate our approach on textttspapi, a production in-vehicle API system at Volvo Group involving 192 endpoints, 420 properties, and 776 CAN signals.<n>The automated workflow achieves 93.7% F1 score while reducing per-API development time from approximately 5 hours to under 7 minutes, saving an estimated 979 engineering hours.
• Score: 8.211397148550782
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multidisciplinary Software Development (MSD) requires domain experts and developers to collaborate across incompatible formalisms and separate artifact sets. Today, even with AI coding assistants like GitHub Copilot, this process remains inefficient; individual coding tasks are semi-automated, but the workflow connecting domain knowledge to implementation is not. Developers and experts still lack a shared view, resulting in repeated coordination, clarification rounds, and error-prone handoffs. We address this gap through a graph-based workflow optimization approach that progressively replaces manual coordination with LLM-powered services, enabling incremental adoption without disrupting established practices. We evaluate our approach on \texttt{spapi}, a production in-vehicle API system at Volvo Group involving 192 endpoints, 420 properties, and 776 CAN signals across six functional domains. The automated workflow achieves 93.7\% F1 score while reducing per-API development time from approximately 5 hours to under 7 minutes, saving an estimated 979 engineering hours. In production, the system received high satisfaction from both domain experts and developers, with all participants reporting full satisfaction with communication efficiency.

Related papers

• LoopsBench: From Harness Engineering to Loop Engineering in Benchmarking Coding Agent [60.27239351179265]
  LOOPSBENCH is a benchmark for loop engineering in coding agent evaluation.<n>It comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains.<n>Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations.
  arXiv  Detail & Related papers  (2026-07-31T20:18:25Z)
• Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam? [90.39633603556767]
  Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested.<n>To quantify this capability, we introduce an evaluation based on China's National Computer Rank Examination (NCRE)<n>We benchmark 7 frontier LLMs and observe stark limitations: single-turn models score a maximum of 36.6%.<n>A stronger agentic system with execution feedback, iterative repair, and broader Office automation access reaches 68.8%, but remains below the 95.5% community-reference score used as a scoring sanity check.
  arXiv  Detail & Related papers  (2026-06-09T14:59:14Z)
• Human-AI Collaboration for Scaling Agile Regression Testing: An Agentic-AI Teammate from Manual to Automated Testing [1.4902707653987912]
  We present an agentic AI approach that generates system-level test scripts directly from validated specifications.<n>Our solution features a retrieval-augmented, multi-agent architecture integrated into Hacon's agile architecture.<n>Results show that the AI teammate significantly increases test script throughput and reduces manual authoring effort.
  arXiv  Detail & Related papers  (2026-03-09T10:19:13Z)
• Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering [0.09046463333989574]
  Real-world software development is organized as a collaborative activity carried out by teams following shared methodologies.<n>We present a fully automated multi-agent system that explicitly models software engineering as an organizational process.<n>Our results suggest that replicating team structure, methodology, and communication is a powerful paradigm for autonomous software engineering.
  arXiv  Detail & Related papers  (2026-02-01T22:17:19Z)
• Towards Reliable ML Feature Engineering via Planning in Constrained-Topology of LLM Agents [1.991571265620589]
  Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering.<n>Their adoption in real-world ML teams remains constrained by critical challenges.<n>We address these challenges with a planner-guided, constrained-topology multi-agent framework.
  arXiv  Detail & Related papers  (2026-01-15T19:33:42Z)
• WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp [0.8197659035200293]
  Report on the industrial deployment of WhatsCode, a domain-specific AI development system that supports WhatsApp.<n>WhatsCode evolved from targeted privacy automation to autonomous agentic integrated with end-to-end feature development and DevOps processes.<n>System committed 692 automated/fix changes, 711 framework adoptions, 141 feature development assists and maintained precision in bug triage.
  arXiv  Detail & Related papers  (2025-12-04T23:25:06Z)
• CoDA: Agentic Systems for Collaborative Data Visualization [57.270599188947294]
  Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations.<n>Existing approaches, including simple single- or multi-agent systems, often oversimplify the task.<n>We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection.
  arXiv  Detail & Related papers  (2025-10-03T17:30:16Z)
• A Production-Ready Machine Learning System for Inclusive Employment: Requirements Engineering and Implementation of AI-Driven Disability Job Matching Platform [20.821562115822182]
  Employment inclusion of people with disabilities remains critically low in Italy, with only 3.5% employed nationally despite mandatory hiring quotas.<n>Our goal is to develop a production-ready machine learning system for disability employment matching that integrates social responsibility requirements while maintaining human oversight in decision-making.<n>The system achieves 90.1% F1-score and sub-100ms response times while processing 500,000 candidate-company combinations in under 10 minutes.
  arXiv  Detail & Related papers  (2025-08-14T12:17:19Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development [65.94639060883475]
  We propose a resource-aware multi-agent system -- Co-Saving.<n>Our key innovation is the introduction of "shortcuts"<n>Compared to the state-of-the-art MAS ChatDev, our method achieves an average reduction of 50.85% in token usage.
  arXiv  Detail & Related papers  (2025-05-28T02:23:53Z)
• Human-In-the-Loop Software Development Agents [12.830816751625829]
  Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks.<n>In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development.<n>We design, implement, and deploy the HULA framework into Atlassian for internal uses.
  arXiv  Detail & Related papers  (2024-11-19T23:22:33Z)
• 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)
• ChatDev: Communicative Agents for Software Development [84.90400377131962]
  ChatDev is a chat-powered software development framework in which specialized agents are guided in what to communicate. These agents actively contribute to the design, coding, and testing phases through unified language-based communication.
  arXiv  Detail & Related papers  (2023-07-16T02:11:34Z)

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.