Related papers: Building an Internal Coding Agent at Zup: Lessons …
Coding agents have received significant adoption in software development recently. Unlike traditional LLM-based code completion tools, coding agents work with autonomy (e.g., invoking external tools) and leave visible traces in software…
As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure the underlying reasoning of generative models, offering…
AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more…
This paper studies the problem of predicting the coding effort for a subsequent year of development by analysing metrics extracted from project repositories, with an emphasis on projects containing XML code. The study considers thirteen…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic…
Production deployment of AI coding agents requires fast, reproducible evaluation signals. Existing industrial practices trade off speed and fidelity: online A/B testing takes weeks and risks user experience, shadow deployment yields signals…
Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined…
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites…
As organizations move toward production deployments of AI agents, which execute non-deterministic workflows, maintain stateful sessions, and often operate with privileged access to internal services, the engineering challenge shifts from…
The study on GitHub Copilot by GovTech Singapore's Engineering Productivity Programme (EPP) reveals significant potential for AI Code Assistant tools to boost developer productivity and improve application quality in the public sector.…
Many industrial IT security standards and policies mandate the usage of a secure coding methodology in the software development process. This implies two different aspects: first, secure coding must be based on a set of secure coding…
Autonomous coding agents increasingly contribute to software development by submitting pull requests on GitHub; yet, little is known about how these contributions integrate into human-driven review workflows. We present a large empirical…
Teams of interacting and co-operating agents have been proposed as an efficient and robust alternative to monolithic centralized control for carrying out specified tasks in a variety of applications. A number of different team and agent…
Despite the growing popularity of AI coding assistants, over 80% of machine learning (ML) projects fail to deliver real business value. This study creates and tests a Machine Learning Canvas, a practical framework that combines business…
Mobile agents research is clearly aiming towards imposing agent based development as the next generation of tools for writing software. This paper comes with its own contribution to this global goal by introducing a novel unifying framework…
High-fidelity vehicle drag evaluation is constrained less by solver runtime than by workflow friction: geometry cleanup, meshing retries, queue contention, and reproducibility failures across teams. We present a contract-centric blueprint…
Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable…
While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal…
Civic grassroots have proven their ability to create useful and scalable software that addresses pressing social needs. Although software engineering plays a fundamental role in the process of creating civic technology, academic literature…