Agentic Software Engineering: Foundational Pillars and a Research Roadmap

2025-09-07

AI Summary

In the Agentic Software Engineering (SE 3.0) era, intelligent agents undertaking complex, goal-directed tasks introduce critical challenges in trustworthiness and human-agent collaboration. Method: This paper proposes a novel agent-centric software engineering paradigm. It introduces a dual-mode “SE for Humans” and “SE for Agents” collaborative framework, featuring an original Agent Command/Execution dual-workbench architecture that supports human-in-the-loop callbacks initiated by agents, structured modeling of engineering activities, and bidirectional human-agent process definition. Key technical innovations include agent team collaboration, task orchestration, Merge-Readiness Packs, and Consultation Request Packs. Contribution: The work establishes the vision and research roadmap for Structured Agent-Centric Software Engineering (SASE), delivering the first scalable, trustworthy SE conceptual framework. It advances human-agent co-engineering toward goal-driven, process-controllable, and verifiable high-assurance software development practices.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Teamwork
• Humans and AI: Human-AI Collaboration / Human-AI Teaming

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.

Problem

• Reimagining software engineering foundations for intelligent agent collaboration
• Designing bidirectional human-AI partnership frameworks for complex objectives
• Establishing structured processes for trustworthy agentic software engineering

Innovation

• Agent Command Environment for human orchestration and mentoring
• Agent Execution Environment for agent task performance
• Structured Agentic Software Engineering redefining human-AI collaboration