Agentic Software Engineering: Foundational Pillars and a Research Roadmap

Authors:
Open Access
Publisher website
Google Scholar
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 in each modality. This new vision of SE requires two distinct, purpose-built workbenches (aka tools) for these two collaborative modalities: the Agent Command Environment (ACE), a command center where humans orchestrate, mentor, and oversee agent teams while managing an inbox of agent-generated events like Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs); and the Agent Execution Environment (AEE), a digital workbench where agents not only execute tasks but can proactively invoke human expertise when facing complex trade-offs or ambiguity. This bidirectional 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.

This publication has 51 references indexed in Scilit: