cs.AIOct 23, 2026

Estimation of Propagated Risk in LLM-based Multi-Agent Systems

Authors: Shreyan Ganguly, Souradeep Chattopadhyay, Qisai Liu, Soumik Sarkar

Organizations: Iowa State University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Large Language Model (LLM) based multi-agent systems introduce a distinctive reliability challenge in which actions taken by upstream agents can affect the correctness of downstream agents. While prior work has investigated error propagation and developed methods for estimating uncertainty inherited from upstream agents, existing approaches do not explicitly model how realized sender-receiver interactions contribute to downstream error risk under different sender correctness states. In this work, we study agent-level error-risk estimation from multi-agent execution traces. We propose Interaction-Effect Propagation (IE-Prop), an interaction-conditioned model that learns separate effects for correct and incorrect upstream agents. For each sender-receiver interaction, the model combines these conditional effects using the sender's estimated error risk, and recursively propagates the resulting risk estimates through the execution graph. We evaluate our approach across three multi-agent architectures and three benchmarks. Across all evaluated architectures, our approach raises the final-node AUROC over the established baseline by approximately 0.05 points on average. Furthermore, tracking risk across multiple agent steps contributes a distinct +0.03 AUROC gain in sequential systems. These results show that realized inter-agent interactions provide predictive information beyond receiver-local evidence, while the value of multi-step risk tracking depends on the system's information-flow structure.

Figures & tables

Figure 1: Error dynamics in LLM-based multi-agent systems: propagation of an upstream error (top), correction of an upstream error (middle), and erroneous override of a correct upstream answer (bottom).
MethodMASProp.Estimator
P(True) ( Kadavath et al., 2022 )––Self-eval.
SelfCheckGPT ( Manakul et al., 2023 )––Sample consistency
Semantic Entropy ( Farquhar et al., 2024 )––Semantic entropy
BTProp ( Hou et al., 2025 )–✓Belief tree
SAUP ( Zhao et al., 2025 )–✓Situation weights
UProp ( Duan et al., 2025 )–✓Information theory
Table 1: Comparison of LLM error-risk estimation methods by multi-agent system (MAS) support, risk propagation (Prop.), and underlying estimation mechanism.
Figure 2: Overview of Interaction-Effect Propagation. (A) Downstream error risk depends on realized sender–receiver interactions rather than monotone error propagation. (B) Interaction effects conditioned on sender correctness are combined using estimated sender risk and receiver-local evidence. (C) Three evaluated multi-agent topologies: sequential, fully connected, and shallow hierarchy.
 GSM8KMedQA
 Verb.MSPEntropyVerb.MSPEntropy
Estimator0.6B1.7B4B0.6B1.7B4B0.6B1.7B4B0.6B1.7B4B0.6B1.7B4B0.6B1.7B4B
Sequential
Receiver-Only0.6220.5310.5180.5410.5870.6780.5700.5880.7200.4950.5160.5310.5080.4860.6860.5120.4860.688
Receiver-Text0.6680.6200.6740.6220.6030.7100.6480.6220.7310.5260.5680.6100.5360.5650.7050.5240.5610.706
Free Learner0.6870.6820.6710.6330.5840.6880.6570.5600.6910.4980.5970.6570.5110.5720.6960.5010.5710.704
Table 2: Final-node AUROC on GSM8K and MedQA by base-model size (Qwen3 0.6B, 1.7B and 4B): in-domain settings, seed mean per model size. Columns are grouped by dataset, then uncertainty signal, then model size. Bold: best value in each column within each topology. Underline: second best value in each column within each topology.
Figure 3: Final-node AUROC on WebQA for sequential and hierarchical systems using MSP and entropy across Qwen3 model sizes, averaged over seeds.
Figure 4: Predicted receiver risk on sequential MedQA traces with correct upstream answers. Top: Risk distributions by receiver correctness. Bottom: Median risk and AUROC across Qwen3 model sizes.
Figure 5: Final-node AUROC gains from recursive risk propagation in the sequential system using Qwen3 models. Cells show gains and corresponding scores (without → with recursion), averaged over three seeds.
Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: The fully connected system. Every agent reads the visible outputs of all earlier agents (six edges). The Alternative-Method agent and the Checker first write a private draft without the earlier outputs; the draft is never passed on.
Figure 7: Cross-dataset transfer performance across three multi-agent topologies, showing final-node AUROC and differences relative to Receiver-Only and PropUQ-MAS baselines.
More in this topic

Multi-Agent LLM Systems

Multi-agent large language model systems coordinate multiple AI agents to solve tasks through communication, specialization, shared tools, and memory.

See all 1,050 papers

Explore similar work

CardsList
Oct 8, 2026

Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources. However, attributing failures in such systems remains challenging because the observed outcome often does not directly reveal the error responsible for the failed execution. In this work, the attribution target is the decisive error, defined as the agent--step pair whose correction would recover the failed execution. Existing approaches largely identify suspicious steps without explicitly modeling how errors propagate across interactions or persist in unresolved loops, making decisive errors difficult to distinguish from downstream failure symptoms. We propose Error-Propagation Modeling for Failure Attribution (EMFA). EMFA constructs a structured representation of the failed trajectory, models both cascading propagation and persistent interaction loops, and uses propagation-aware candidate screening followed by counterfactual verification to identify the decisive agent--step pair. On the Who&When benchmark, EMFA achieves state-of-the-art step-level attribution accuracy and remains competitive at the agent level. It improves the previous best step-level results by 3.45 and 4.40 percentage points on the Hand-Crafted and Algorithm-Generated subsets, respectively.

Jiaqi Liao, Yuanzhao Zhai, Huanxi Liu +5

College of Computer Science and Technology, National University of Defense Technology; State Key Laboratory of Complex & Critical Software Environment, Changsha, Hunan, China · School of Mechanical Engineering, Tianjin University, Tianjin, China · College of Computer Science and Technology, National University of Defense Technology; National Key Laboratory of Parallel and Distributed Computing, Changsha, Hunan, China

Failure Attribution for LLM AgentsAgent Failure AnalysisMulti-Agent LLM SystemsMulti-Agent Systems
AskPDF
Aug 22, 2026

PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems

LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond isolated agent failures. For instance, errors in intermediate messages could be inherited and amplified by downstream agents. Existing uncertainty quantification (UQ) methods mainly target isolated responses or single-agent reasoning, and therefore fail to capture uncertainty propagation in MAS. To this end, we propose PropUQ-MAS, an error propagation-aware UQ framework that represents MAS execution as a communication-structured graph and estimates each step's reliability by combining local uncertainty with uncertainty inherited from upstream messages. Extensive experiments demonstrate that PropUQ-MAS consistently improves UQ in MAS, with average relative gains of +6.10% in AUROC and +47.58% in PRR.

Yaokun Liu, Yifan Liu, Daniel Yue Zhang +3

University of Illinois Urbana-Champaign · Scale AI

Multi-Agent LLM SystemsLLM Uncertainty EstimationUncertainty Propagation
AskPDF
Jul 28, 2026

Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks

This paper investigates how multi-agent systems (MAS)-based on large language models (LLMs) can support actuarial risk modelling, with a particular focus on uncertainty quantification. Actuarial workflows represent a high-stakes decision-support setting where unreliable outputs may lead to incorrect risk assessment, unfair pricing, and regulatory non-compliance. To address uncertainty introduced by the probabilistic nature of LLMs and dependencies between agents, a multi-agent framework is proposed in which specialised agents perform data preparation, modelling, review, and explanation tasks under a central hub. The main contribution is a novel approach to uncertainty propagation using token-level log-probabilities and a Bayesian Network. Importantly, log probabilities are not treated as direct probabilities of correctness or task success. Instead, length-normalised log-probability summaries are transformed into calibrated task-level confidence estimates before incorporation into the Bayesian Network. Results show that the framework reproduces baseline actuarial performance while providing additional insight into workflow stability and runtime uncertainty propagation.

Bart Custers, Koorosh Aslansefat

University of Hull, Hull HU6 7RX, UK

Multi-Agent LLM SystemsUncertainty QuantificationBayesian NetworksUncertainty Propagation
AskPDF