POLARIS: Is Multi-Agentic Reasoning the Next Wave in Engineering Self-Adaptive Systems?
Divyansh Pandey, Vyakhya Gupta, Prakhar Singhal, Karthik Vaidhyanathan
TL;DR
POLARIS proposes a three-layer, multi-agent framework for AI-native self-adaptation, integrating an Adapter, a reasoning-driven Reasoner, and a Meta-Learner to enable proactive, learnable, and coordinated adaptation. By coupling low-latency reactive control with deliberative planning and long-horizon meta-learning, POLARIS demonstrates improved performance and generalization on two self-adaptive exemplars (SWIM and SWITCH) and outlines a shift toward Self-Adaptation 3.0, where systems reason about and evolve their own adaptation processes. The work highlights the benefits of agentic AI—tool-aware reasoning, experiential memory, and continual policy evolution—for resilient, goal-directed behavior in dynamic environments. It also raises important questions about assurance, prompt design, and human-in-the-loop integration as these AI-native adaptive systems mature.
Abstract
The growing scale, complexity, interconnectivity, and autonomy of modern software ecosystems introduce unprecedented uncertainty, challenging the foundations of traditional self-adaptation. Existing approaches, typically rule-driven controllers or isolated learning components, struggle to generalize to novel contexts or coordinate responses across distributed subsystems, leaving them ill-equipped for emergent unknown unknowns. Recent discussions on Self-Adaptation 2.0 emphasize an equal partnership between AI and adaptive systems, merging learning-driven intelligence with adaptive control for predictive and proactive behavior. Building on this foundation, we introduce POLARIS, a three-layer multi-agentic self-adaptation framework that advances beyond reactive adaptation. POLARIS integrates: (1) a low-latency Adapter layer for monitoring and safe execution, (2) a transparent Reasoning layer that generates and verifies plans using tool-aware, explainable agents, and (3) a Meta layer that records experiences and meta-learns improved adaptation policies over time. Through shared knowledge and predictive models, POLARIS handles uncertainty, learns from past actions, and evolves its strategies, enabling systems that anticipate change and maintain resilient, goal-directed behavior. Preliminary evaluation on two self-adaptive exemplars, SWIM and SWITCH, shows that POLARIS consistently outperforms state-of-the-art baselines. We argue this marks a shift toward Self-Adaptation 3.0, akin to Software 3.0: a paradigm where systems not only learn from their environment but also reason about and evolve their own adaptation processes, continuously improving to meet novel challenges.