APEX: Adaptive Principle EXtraction A Three-Layer Self-Evolution Framework for Production AI Agents
Quick Answer
APEX introduces a three-layer co-evolution framework for AI agents, achieving a 90% improvement in health score over baseline.
Quick Take
Implemented on Joe, a production-grade super AI agent, it distills six novel principles and optimizes workflow topology, demonstrating superior performance compared to traditional single-axis optimization methods.
Key Points
- APEX achieves an APEX Health Score of 0.570, up from 0.300 baseline.
- Implemented on Joe, designed for NVIDIA Agent Challenge 2026.
- Distilled six novel reusable principles during the evolutionary run.
- Selected a workflow topology scoring 0.900, a 20% improvement.
- Cost of implementation was only 4 calls, approximately 270 seconds.
Paper Resources
Source Excerpt
arXiv:2606. 15363v1 Announce Type: new Abstract: 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 -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. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.