Papers for

embedded software teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Llm agents improve firmware coding through iterative testing and repair

Closed-loop evaluation of LLM agents for embedded software development

Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is a demanding target because correctness depends on closed-loop behavior under sensing, timing, and safety constraints, not only on static source quality. Yet embedded-agent evaluation remains limited and often emphasizes one-shot synthesis or offline correctness. We present a benchmark for closed-loop evaluation of embedded coding agents. Each task provides a plain-text engineering description, constrained workspace, and visible build-and-runtime surface. The agent must translate requirements into implementation and self-verification steps, then iterate until the required device behavior is achieved. The suite contains five embedded-control tasks and four feedback scenarios: one-shot generation, realistic self-verification, CI-style red/green feedback, and oracle-style detailed feedback. The implementation targets simulated ESP32 firmware for reproducibility. We evaluate seven GPT-family and Qwen-family configurations across five tasks and four scenarios, with three repetitions per condition for 420 runs. gpt-5.4 has the highest pass rate among evaluated configurations but does not saturate the benchmark; qwen3.5-27B is the strongest observed local model; and smaller local models degrade sharply in pass rate and search efficiency. These results suggest that capable local embedded coding agents are emerging.

Thu 8 OctSoftware EngineeringArtificial IntelligenceHardware Architecture
The gist
Writing software for devices like microcontrollers is tough because the code must work correctly in real-time and under specific safety conditions. This paper introduces a new way to test how well large language models (LLMs) can write, test, and fix embedded software by simulating this real-world process repeatedly. The authors evaluated several LLMs on tasks involving simulated firmware for a common microcontroller and found that more advanced models performed better but still have room to improve. This helps show how close these AI tools are to being reliable assistants for embedded software development.
Open → 2610.11447v1

Embedded software firms prepare for AI agents to reshape teams and tasks

Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development

Abstract: The emergence of AI agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executing, and evaluating development tasks with increasing autonomy. This transition is particularly significant for embedded software organizations, where strict requirements for quality, traceability, verification, and long-term maintainability often apply. This paper presents a case study of a large embedded systems company and its transition toward becoming an AI-first organization. Through a mixed method, we analyzed data collected from a semi-structured workshop with 40 participants, including scrum masters, architects, management, and product owners. The findings show that the participants expect agentic AI to affect team structure, required competencies, organizational strategies, and developers' roles within the organization. Based on these findings, the paper discusses implications for federated AI team formation, human-in-the-loop practices in such an organization, and the sustainable adoption of AI agents in embedded software engineering. We also present a concrete roadmap for the organization towards becoming an AI-first organization.

Fri 25 SeptSoftware EngineeringArtificial Intelligence
The gist
AI tools are becoming more than just helpers for programmers—they are starting to take on tasks like planning and checking software development work on their own. This change is important for companies that build software embedded in devices, which require very careful quality checks and long-term support. The authors studied a large company moving to put AI agents at the center of its work. They found that AI will change how teams are structured, what skills people need, and how organizations plan their work, and they created a detailed plan to help the company become AI-first.
Open → 2609.30863v1