APEX: Adaptive Principle EXtraction A Three-Layer Self-Evolution Framework for Production AI Agents

Computer Science > Artificial Intelligence [Submitted on 13 Jun 2026] APEX: Adaptive Principle EXtraction A Three-Layer Self-Evolution Framework for Production AI Agents Ya-Chuan Chen, Tien-Jen Lai, Hsiang-Wei Hu Self-improvement in AI agents has emerged as a key research frontier: systems that modify their own prompts, workflows, and decision rules based on accumulated operational experience. The state-of-the-art Self-Harness framework [1] achieves 14--21% improvement on Terminal-Bench-2.0 by mining failure clusters and patching the agent harness. However, Self-Harness optimises only one dimension -- the prompt harness -- leaving behavioural principles and workflow topology unchanged. We propose APEX (Adaptive Principle EXtraction), a three-layer co-evolution framework that simultaneously evolves: (L1) the harness via failure-mode patching, (L2) behavioural principles via success-trace distillation [2], and (L3) the agent workflow topology via structural fitness-based selection [6]. We implement APEX on Joe [13], a production-grade super AI Agent built on NVIDIA Nemotron and designed as an Edge AI Agent Factory for the NVIDIA Agent Challenge 2026, managing a 15-node compute fleet using 114 real task traces collected over 18 days. APEX achieves an APEX Health Score of 0.570 (+90% vs. baseline 0.300) in a single evolutionary run, distilling 6 novel reusable principles and selecting a research-first workflow topology scoring 0.900 (+20%). Our results demonstrate that multi-dimensional co-evolution substantially outperforms single-axis harness optimisation, at a cost of only 4 LLM calls (~270 s) on a local qwen2.5-coder:32b instance. Comments: 8 pages, 1 figure, 4 tables. Evaluated on a production 15-node compute fleet with 114 real task traces. Code available at this https URL Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.15363 [cs.AI]   (or arXiv:2606.15363v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.15363 Focus to learn more Submission history From: Ya-Chuan Chen [view email] [v1] Sat, 13 Jun 2026 15:47:27 UTC (12 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 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?)