This work uses event logs extracted from software repositories to discover project-specific agent roles using a predefined SE role vocabulary grounded in repository behavior and generates matching agent specifications and implementations that are aligned with human expectations.
Abstract
Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents may introduce unmanageable complexity, whereas micro-agents may create severe coordination overhead. Moreover, existing multi-agent SE frameworks typically rely on predefined role structures and do not account for project-specific characteristics or process adaptations. We address this by combining object-centric, imperative, and declarative process mining. Using event logs extracted from software repositories, our approach discovers project-specific agent roles using a predefined SE role vocabulary grounded in repository behavior and generates matching agent specifications and implementations. As proof-of-concept, we applied our approach to a well-established open-source project. We performed functional tests and an exploratory user study to determine how well the generated AI agent specifications are aligned with human expectations.
Enterprise-modeling (EM) tools are often complex and hard to extend. Yet, users may want to explore new EM features and capabilities that currently do not exist. AI coding agents can help here by enabling the development of new capabilities and entire tools, but whether we can trust a modeling-language tool an LLM largely wrote remains a question. This paper reports on the AI-assisted construction of PM4Py-UCM, an open-source tool that mines Use Case Map (UCM) models from event logs. PM4Py-UCM's capabilities include some expected from process mining tools (e.g., performance heat-maps and dashboards) and distinctive ones (e.g., mined executable scenarios/variants, and model decomposition). We mined the development record itself, composed of 18 agent sessions (374 human turns and 10,328 tool actions over 65 hours), 151 commits, 20 releases, and a test suite grown from 108 to 691 test functions, in order to characterize, in a single in-depth case, how the tool was built with an agent (Claude Code), complemented by an independent static assessment of the resulting code (coverage, complexity, maintainability, security, architecture). We contribute a reproducible, privacy-preserving toolkit and taxonomy that classify human turns and flag cross-cutting consistency work, agent corrections, and retracted requests. Up to version 0.7.4, fixes outnumber features 2.3:1, with ~18% of turns for correcting agent errors. Feature waves dragged a measurable tail of documentation/test/notebook consistency work, and tests grew lockstep with features. We finally present lessons learned, centered on making model transformations mechanically checkable, and the oracle-based validation strategy that closed the"the agent said it works"gap, for responsibly engineering EM tooling with AI.
Overall, repository-preserved Agent Plans under these tool-specific directories appear to be a narrow but informative artifact for studying task intent and execution guidance in human-agent workflows.
M. Abubakar, Seyedmoein Mohsenimofidi, Jai Lal Lulla et al.· 1 citation
This study characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle, offering a more nuanced understanding of their benefits and limitations in real-world practices.
Iren Mazloomzadeh, Mohammad Mehdi Morovati, F. Khomh· 0 citations
Large language models (LLMs) have evolved from standalone generative systems into agentic AI systems capable of planning, reasoning, tool use, and multi-agent collaboration. Enterprises are increasingly adopting AI agents to automate and orchestrate complex workflows, from IT operations to employee productivity. While early deployments focused on proof-of-concept prototypes, the past year has marked a clear shift toward production-grade enterprise AI agents. This transition has been enabled by a wave of new technologies, including multi-agent orchestration, memory and state management, skill-based and modular agent architectures, and deeper integration with enterprise data and workflow platforms, which together make scalable, reliable agent systems feasible in practice. At the same time, moving agents into production introduces new technical and organizational challenges, such as rigorous evaluation and benchmarking, security and governance, and system design for long-running, autonomous operation. Building on the success of our two prior highly attended editions: ''Agentic AI for Enterprise'' workshop at KDD 2025 and ''Enterprise RAG'' workshop at CIKM 2024, this workshop aims to bring together researchers and practitioners to examine how enterprise AI agents can successfully move from prototypes to production. We focus on three pillars: 1) Agent architectures and systems; 2) Enterprise applications and deployments; 3) Evaluation and governance.
Min Du, Anbang Xu, Jasmine Jaksic et al.· Proceedings of the 32nd ACM...· 0 citations
We are witnessing the emergence of Agentic Software Engineering (SE~3.0), where AI agents act as autonomous AI Teammates performing complex tasks such as coding, debugging, and testing. As AI Teammates generate a vast new category of digital artifacts, they introduce unique opportunities and challenges related to human-AI collaboration, trustworthiness, and economic impact. This workshop serves as the premier forum for addressing these challenges, anchored by the launch of the AIDev dataset. Comprising over one million agentic pull requests generated by AI Teammates such as Claude Code, OpenAI Codex, and GitHub Copilot, AIDev provides the empirical evidence needed to understand the behaviors of AI Teammates. This workshop features insights from major industry players and academic pioneers, and aims to define a roadmap for a world where AI Teammates and human developers build the future together.
Hao Li, Haoxiang Zhang, Jie M. Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
AI agents are evolving from answer engines into persistent teams that use tools, delegate work, learn from experience, and modify the artifacts that shape their future behavior. The defining question for deployment is no longer merely what agents can do, but who controls what they are allowed to become. We introduce logos, a pluggable layer for self-evolution and governance that strengthens existing multiagent frameworks rather than replacing them. logos compiles heterogeneous multimodal inputs, including documents, images, audio, tables, databases, APIs, and human instructions into versioned agent packs containing agents, tools, knowledge, tests, permissions, and policies. During operation, it transforms agent activity into portable, auditable event traces and applies fail-closed verification across frameworks and backends. Every learned prompt, memory, skill, tool, role, or workflow remains an untrusted release candidate until held-out execution evidence, human-controlled policy, and explicit authorization permit its promotion. This architecture enables"verifiable human-agent loop engineering": agents can act, ask, learn, and propose improvements, while humans can steer objectives, permissions, approvals, and irreversible actions without interrupting continuous operation. logos provides a living logic for accountable automation. Agents may evolve at machine speed, but only evidence and human authority can close the loop.
Yuma Ichikawa, Yamato Arai, Kosaku Kimura et al.· 0 citations