PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems

2026-09-29

AI Summary

This study addresses the scalability and reliability bottlenecks of existing LLM-based multi-agent systems in large-scale, high-concurrency scenarios by proposing a decentralized architecture. The method introduces a novel Web-of-Trust governance model that decouples communication from orchestration strategies, enabling flexible switching among star, chain, and mesh topologies. Furthermore, it facilitates self-organizing team formation through capability discovery and incorporates a dynamic fault recovery mechanism to ensure system robustness. Evaluated on the HotPotQA benchmark, the proposed system scales to thousands of agents with millisecond-level team assembly, achieving an eightfold improvement in overall efficiency while maintaining a 100% task completion rate under node failures.

Abstract

Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to support large numbers of agents and concurrent tasks, tolerate failures, govern agent interactions, and accommodate the diverse planning and execution patterns different tasks require. We present PANDA, a decentralized architecture that connects a large collective of heterogeneous, independently administered agents, letting them discover each other's capabilities and self-organize into small specialized teams per task. PANDA scales by decoupling collective communication from team communication, allowing agents to participate in multiple teams simultaneously, load-balancing tasks across the collective, and scheduling concurrent work within each agent. PANDA further separates the underlying architecture from the orchestration strategy, supporting three planning and execution patterns (star, chain, and mesh) that can be selected according to the structure and requirements of each task. PANDA detects infrastructure and orchestration failures and recovers affected tasks by dynamically replanning around failed components. Finally, to provide governance without a centralized service that would limit scalability, PANDA uses a web-of-trust model to constrain agent interactions to established trust relationships. We evaluate PANDA on the HotPotQA benchmark, demonstrating that it scales to thousands of agents, assembles teams in milliseconds, matches state-of-the-art accuracy at up to 8x the efficiency, and sustains 100% task completion under faults where existing systems fail.

Problem

• Multi-Agent Systems
• Scalability
• Fault Tolerance
• Decentralized Architecture
• Task Orchestration

Innovation

• Decentralized Architecture
• Multi-Agent Systems
• Flexible Orchestration
• Fault Tolerance
• Web-of-Trust