ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value alignment is typically evaluated for isolated models, how value perturbations propagate through agent interactions remains poorly understood. We present ValueFlow, a perturbation-based framework that measures value drift in multi-agent systems via a 56-value valuation dataset derived from the Schwartz Value Survey, with agent value orientations scored using an LLM-as-a-judge protocol. ValueFlow decomposes value drift into agent-level response behavior and system-level structural effects, captured by two metrics: \b{eta}-susceptibility, an agent's sensitivity to perturbed peer value signals, and system susceptibility (SS), the effect of node-level perturbations on final system outputs.Experiments span across value dimensions, backbones, personas, and topologies, showing that susceptibility varies sharply across values and is strongly shaped by interaction structure, indicating that value alignment in multi-agent systems is a system-level property, not just an agent-level one. ValueFlow thus provides a principled basis for auditing and mitigating value propagation in deployed multi-agent systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles. Value-based approaches offer a m…
Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking
Training query-propagation end-to-end multi-object tracking (MOT) models requires dense bounding-box and identity annotations across video sequences, making dataset construction expensive. Clip-level active learning redu…
Multi-Object TrackingActive LearningAn Application of Backpropagation Artificial Neural Network Method for Measuring The Severity of Osteoarthritis
The examination of Osteoarthritis disease through X-ray by rheumatology can be classified into four grade of severity. This paper discusses about the application of artificial neural network backpropagation method for me…
QuantizationQUIVER: A Formal Framework for Quantifying Perturbation Propagation and Bifurcation in Compound AI Systems
Compound AI systems that chain multiple LLM calls into directed computation graphs are now the dominant architecture for production AI. Although these architectures leverage heterogeneous nodes with mixed-mode outputs, n…
Noise propagation and MP-PCA image denoising for high-resolution quantitative T2* and magnetic susceptibility mapping (QSM)
Quantitative Susceptibility Mapping (QSM) is a technique for measuring magnetic susceptibility of tissues, aiding in the detection of pathologies like traumatic brain injury and multiple sclerosis by analyzing variations…
DenoisingDiagnosticImage Denoising