Trace-Level Analysis of Information Contamination in Multi-Agent Systems

2026-04-30

AI Summary

This work investigates how external uncertainties propagate through structured multi-agent workflows to induce information contamination, thereby degrading reasoning trajectories and output correctness. We introduce a taxonomy of three distinct manifestations of information contamination along with their control-flow characteristics, establishing the first classification framework tailored to structured multi-agent workflows and a trajectory-based detection and localization methodology. Through systematic injection of structured perturbations across 32 GAIA tasks and 614 experimental configurations involving three diverse models, we uncover a decoupling between workflow structural divergence and answer correctness, exposing the fundamental limitations of current validation mechanisms. These findings provide empirical grounding for the design of robust, defense-oriented multi-agent workflows.

Abstract

Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively extract, transform, and reference external information. In these workflows, uncertainty is not merely an input-quality issue: it can redirect decomposition and routing decisions, reshape intermediate state, and produce qualitatively different execution trajectories. We study this phenomenon by treating uncertainty as a controlled variable: we inject structured perturbations into artifact-derived representations, execute fixed workflows under comprehensive logging, and quantify contamination via trace divergence in plans, tool invocations, and intermediate state. Across 614 paired runs on 32 GAIA tasks with three different language models, we find a decoupling: workflows may diverge substantially yet recover correct answers, or remain structurally similar while producing incorrect outputs. We characterize three manifestation types: silent semantic corruption, behavioral detours with recovery, and combined structural disruption and their control-flow signatures (rerouting, extended execution, early termination). We measure operational costs and characterize why commonly used verification guardrails fail to intercept contamination. We contribute (i) a formal taxonomy of contamination manifestations in structured workflows, (ii) a trace-based measurement framework for detecting and localizing contamination across agent interactions, and (iii) empirical evidence with implications for targeted verification, defensive design, and cost control.

Problem

• information contamination
• multi-agent systems
• uncertainty propagation
• structured workflows
• trace divergence

Innovation

• information contamination
• multi-agent systems
• trace divergence
• structured workflows
• uncertainty injection