MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems

arXiv:2602.13671v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation and lack adaptability after deployment. We study in-context structural adaptation, where structured experience conditions both query-dependent system generation and execution-time reconfiguration without updating LLM parameters. We introduce MASFly, which realizes this adaptation through two complementary mechanisms. First, a retrieval-augmented SOP instantiation mechanism retrieves and adapts successful collaboration patterns to construct a query-specific MAS. Second, an experience-enhanced process supervision mechanism uses a dedicated Watcher agent to monitor execution against prior failure experience and reconfigure the system upon abnormal behavior. Experiments demonstrate that MASFly achieves state-ofthe-art performance, including a 61.7% success rate on TravelPlanner, with strong task adaptability and robustness.

Related

• Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
• Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
• Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
• extsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer

Source: arXiv cs.AI | 2026-09-01