Skip to content
Preprint

AgentSoV: Virtual Sensing for LLM Multi-Agent Systems via Stream of Variation

Oct 2026 · 0 citations · 47 references
Computer Science Engineering

TL;DR

AgentSoV reframes agentic execution as a dynamic system to model rather than merely text to inspect, providing insights for MAS structure and component design and demonstrating a unified approach to fault localization, information influence, and observability.

Abstract

Large language model (LLM) multi-agent systems (MASs) solve complex tasks through interacting agents, yet their reliability is difficult to analyze because failures depend on both individual agents and how information and errors propagate across the system. Existing approaches largely treat this as post-hoc failure attribution, but do not provide a common model across heterogeneous MAS architectures or support broader analysis of information influence and observability. We introduce AgentSoV, a virtual-sensing framework that models MAS execution as a stochastic dynamic system through Stream of Variation (SoV). AgentSoV maps heterogeneous trajectories into diagnostic stages, constructs virtual measurements from observable outputs, and learns cross-stage variation propagation with a state-space model. Its representation is architecture-aware in stage dependencies yet architecture-agnostic in analytical language, supporting chain-structured, orchestration-based, and directed acyclic graph (DAG)-structured MASs. Without re-executing the MAS, AgentSoV supports three system-level analyses: failure attribution identifies where abnormal variation enters; stage-input influence quantifies how strongly intermediate inputs affect downstream outcomes; and virtual-sensor placement selects complementary observations under a monitoring budget. Experiments across multiple MAS architectures demonstrate a unified approach to fault localization, information influence, and observability. AgentSoV reframes agentic execution as a dynamic system to model rather than merely text to inspect, providing insights for MAS structure and component design.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability

MASBench is introduced, a multi-agent collaboration benchmark designed under partially observable constraints that provides deterministic evaluation metrics, including performance score, communication cost, and cost effectiveness, to characterize both collaboration outcomes and communication overhead.

Qi-Zhi Chu, Ze-Kai Yu, Si-Jie Wen et al. · 1 citation
#artificial intelligence Preprint Oct 2026

MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification

Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordinating complementary capabilities. Despite extensive research on MAS, existing work largely focuses on specific aspects or individual phases of their development and op...

He-Hai Lin, Zi-Xuan Wang, Ming Yan et al. · 1 citation
Preprint Sep 2026

LLM-Based Multi-Agent Systems over Wireless Networks: A Joint Agent--Network Design Perspective

As large language models (LLMs) evolve from standalone models into collaborative agents embedded in physical systems, their reasoning and execution are increasingly distributed across wireless edge nodes. In this setting, wireless networks are experiencing a paradigm shift from only providing data connectivity to suppo...

Chao Hu, Yuan-Cheng Guo, Guan-Lin Wu et al. · 0 citations
Preprint Sep 2026

Scaling Multi-Agent Systems with Prospect-State Propagation

A phenomenon in which agent heterogeneity gradually decreases during simulation is revealed, and Prospect-State Propagation for Multi-Agent Systems (PspMAS) is proposed, Inspired by prospect theory, which decouples each agent's micro state into a compact Prospect State and an expressive Semantic State.

Zhi-Mei Chen, Mu Chen, Fakhri Karray · 0 citations
#natural language process... Preprint Oct 2026

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

ScaleMAS is built, where asynchronous agents interact with a shared datastore of linked messages via three operations: publishing messages with optional references to earlier ones that they build on, searching for messages by content, and visiting messages by address, which is an effective proxy for quality.

Zhen-Ting Qi, Zhuo-Kai Zhao, Ru-Lin Shao et al. · 0 citations
#artificial intelligence Preprint Oct 2026

When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems

LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protocols, remote tools, and model endpoints exposes communication to message loss, delay, and context expiration. Because agents often exchange open-ended natural language, ano...

Jin-Hao Zhou, Xiao-Yue Zhang, Jiongchi Yu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.