# Agentic Software Engineering: Foundational Pillars and a Research Roadmap

arXiv: https://arxiv.org/abs/2509.06216 · HTML: https://mlsanity.com/paper/2509.06216/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 62 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 26 of 26)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models](https://mlsanity.com/paper/2210.03162/) (2022)
- [Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers](https://mlsanity.com/paper/2506.13538/) (2025)
- [Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study](https://mlsanity.com/paper/2503.15223/) (2025)
- [Extending Context Window of Large Language Models via Semantic Compression](https://mlsanity.com/paper/2312.09571/) (2023)
- [Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap](https://mlsanity.com/paper/2410.06107/) (2024)
- [SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning](https://mlsanity.com/paper/2502.20127/) (2025)
- [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024)
- [The Current Challenges of Software Engineering in the Era of Large Language Models](https://mlsanity.com/paper/2412.14554/) (2024)
- [From Today's Code to Tomorrow's Symphony: The AI Transformation of Developer's Routine by 2030](https://mlsanity.com/paper/2405.12731/) (2024)
- [Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents](https://mlsanity.com/paper/2411.03455/) (2024)
- [Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models](https://mlsanity.com/paper/2410.09012/) (2024)
- [PromptExp: Multi-granularity Prompt Explanation of Large Language Models](https://mlsanity.com/paper/2410.13073/) (2024)
- [Galapagos: Automated N-Version Programming with LLMs](https://mlsanity.com/paper/2408.09536/) (2024)
- [SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving](https://mlsanity.com/paper/2505.23932/) (2025)
- [Context-Aware CodeLLM Eviction for AI-assisted Coding](https://mlsanity.com/paper/2506.18796/) (2025)
- [Hear Your Code Fail, Voice-Assisted Debugging for Python](https://mlsanity.com/paper/2507.15007/) (2025)

## Built on by (most cited first, 30 of 41)

- [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025)
- [Agentic Refactoring: An Empirical Study of AI Coding Agents](https://mlsanity.com/paper/2511.04824/) (2025)
- [Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned](https://mlsanity.com/paper/2603.05344/) (2026)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [PPTArena: A Benchmark for PowerPoint Editing](https://mlsanity.com/paper/2512.03042/) (2025)
- [Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems](https://mlsanity.com/paper/2512.12791/) (2025)
- [How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests](https://mlsanity.com/paper/2601.17581/) (2026)
- [OpenClaw AI Agents as Informal Learners at Moltbook: Characterizing an Emergent Learning Community at Scale](https://mlsanity.com/paper/2602.18832/) (2026)
- [Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub](https://mlsanity.com/paper/2601.00477/) (2026)
- [Codified Context: Infrastructure for AI Agents in a Complex Codebase](https://mlsanity.com/paper/2602.20478/) (2026)
- [AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub](https://mlsanity.com/paper/2604.03551/) (2026)
- [Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality](https://mlsanity.com/paper/2607.03691/) (2026)
- [Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary](https://mlsanity.com/paper/2510.19692/) (2025)
- [Why Agentic-PRs Get Rejected: A Comparative Study of Coding Agents](https://mlsanity.com/paper/2602.04226/) (2026)
- [Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development](https://mlsanity.com/paper/2603.14805/) (2026)
- [Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering](https://mlsanity.com/paper/2604.16790/) (2026)
- [HAFixAgent: History-Aware Program Repair Agent](https://mlsanity.com/paper/2511.01047/) (2025)
- [Human-AI Synergy in Agentic Code Review](https://mlsanity.com/paper/2603.15911/) (2026)
- [Agentic Coding Needs Proactivity, Not Just Autonomy](https://mlsanity.com/paper/2605.06717/) (2026)
- [Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering](https://mlsanity.com/paper/2606.17799/) (2026)
- [Walking the Tightrope of LLMs for Software Development: A Practitioners' Perspective](https://mlsanity.com/paper/2511.06428/) (2025)
- [N-Version Programming with Coding Agents](https://mlsanity.com/paper/2606.20158/) (2026)
- [From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems](https://mlsanity.com/paper/2603.20300/) (2026)
- [Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs](https://mlsanity.com/paper/2603.27524/) (2026)
- [Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development](https://mlsanity.com/paper/2604.16323/) (2026)
- [RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow](https://mlsanity.com/paper/2604.22217/) (2026)
- [Toward Agentic Software Project Management: A Vision and Roadmap](https://mlsanity.com/paper/2601.16392/) (2026)
- [CovAgent: Overcoming the 30% Curse of Mobile Application Coverage with Agentic AI and Dynamic Instrumentation](https://mlsanity.com/paper/2601.21253/) (2026)
- [Supporting software engineering tasks with agentic AI: Demonstration on document retrieval and test scenario generation](https://mlsanity.com/paper/2602.04726/) (2026)
- [Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review](https://mlsanity.com/paper/2604.13103/) (2026)

## Abstract (arXiv)

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.