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.

翻译：AI智能体的自我改进已成为关键研究前沿：系统能够根据积累的运筹经验自主修改自身提示、工作流程与决策规则。当前最先进的Self-Harness框架[1]通过挖掘失败簇并修补智能体控制框架，在Terminal-Bench-2.0基准上实现了14%-21%的性能提升。然而Self-Harness仅优化单个维度——提示控制框架，未改变行为原则与工作流程拓扑结构。本文提出APEX（自适应原则提取）——一种三层联合进化框架，同步进化：(L1)通过失败模式修补控制框架；(L2)通过成功轨迹蒸馏[2]优化行为原则；(L3)通过结构适应度选择[6]优化智能体工作流拓扑。我们将APEX应用于Joe[13]——一个基于NVIDIA Nemotron构建的生产级超级AI智能体，该智能体专为NVIDIA Agent Challenge 2026设计为边缘AI智能体工厂，利用18天内采集的114个真实任务轨迹管理15节点计算集群。单次进化运行中，APEX实现了0.570的APEX健康评分（较基线0.300提升90%），提炼出6条可复用新原则，并选择得分为0.900（+20%）的研究优先型工作流拓扑。实验结果表明，多维联合进化显著优于单轴控制框架优化，且在本地qwen2.5-coder:32b实例上仅需4次LLM调用（约270秒）。