← Back ◬ AI & Machine Learning Mar 19, 2026

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

arXiv AI Archived Mar 19, 2026 ✓ Full text saved

arXiv:2603.18000v1 Announce Type: new Abstract: Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task re-execution in complex scenarios. We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code rather than textual experience. Crucially, these subagents are

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Artificial Intelligence [Submitted on 18 Mar 2026] AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse Zhang Zhang, Shuqi Lu, Hongjin Qian, Di He, Zheng Liu Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task re-execution in complex scenarios. We propose AgentFactory, a new self-evolution paradigm that preserves successful task solutions as executable subagent code rather than textual experience. Crucially, these subagents are continuously refined based on execution feedback, becoming increasingly robust and efficient as more tasks are encountered. Saved subagents are pure Python code with standardized documentation, enabling portability across any Python-capable system. We demonstrate that AgentFactory enables continuous capability accumulation: its library of executable subagents grows and improves over time, progressively reducing the effort required for similar tasks without manual intervention. Our implementation is open-sourced at this https URL, and our demonstration video is available at this https URL. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.18000 [cs.AI] (or arXiv:2603.18000v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2603.18000 Focus to learn more Submission history From: Zhang Zhang [view email] [v1] Wed, 18 Mar 2026 17:58:25 UTC (545 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev | next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes