PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 18 of its 34 references that are in the map. First posted on arXiv 22 Aug 2026.
Builds on
18 of 34 references.
Closest ancestors · 6
Same direction, newest first
- 2026Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition9 Apr
- 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making20 Jun
- 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning7 Feb
- 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
- 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks4 Jun
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar
Other references · 12
- 2021Training Verifiers to Solve Math Word Problemscited by 9,916
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,758
- 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,362
- 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,001
- 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 960
- 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 800
- 2025Why Do Multi-Agent LLM Systems Fail?cited by 573
- 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
- 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 159
- 2026Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answeringcited by 2
- 2026Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignmentcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents
- 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
- 2026Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
- 2026MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems
- 2026Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems
- 2024SAUP: Situation Awareness Uncertainty Propagation on LLM Agent
- 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
- 2025SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication