# Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/2607.00972 · HTML: https://mlsanity.com/paper/2607.00972/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 11 of 11)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making](https://mlsanity.com/paper/2506.17419/) (2025)
- [RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs](https://mlsanity.com/paper/2509.03768/) (2025)
- [SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance](https://mlsanity.com/paper/2410.10852/) (2024)
- [Prescriptive Agents based on RAG for Automated Maintenance (PARAM)](https://mlsanity.com/paper/2508.04714/) (2025)
- [Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models](https://mlsanity.com/paper/2508.10192/) (2025)
- [DScheLLM: Enabling Dynamic Scheduling through a Fine-Tuned Dual-System Large language Model](https://mlsanity.com/paper/2601.09100/) (2026)

## Built on by (most cited first, 2 of 2)

- [Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks](https://mlsanity.com/paper/2607.25877/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)

## Abstract (arXiv)

Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines may fail. This paper presents an uncertainty-aware Agentic Retrieval-Augmented Generation (RAG) framework in which planner, evaluator and generator stages produce uncertainty signals derived from semantic divergence and generator self-evaluation. These signals are propagated through a Bayesian Network (BN) to estimate system-level uncertainty and provide node-level indicators of potential failure points across the workflow. The approach is evaluated on StrategyQA and HotpotQA using GPT-3.5-Turbo and GPT-4.1-Nano, with Area Under the Receiver Operating Characteristic Curve (AUROC), Area Under the Accuracy-Rejection Curve (AUARC), Expected Calibration Error (ECE), and Brier Score used to assess discrimination, selective prediction and calibration. Results show that Bayesian propagation is more effective on HotpotQA, where uncertainty accumulates across multi-hop reasoning stages, while StrategyQA exposes limitations caused by miscalibration and unreliable upstream signals. The study positions Bayesian uncertainty propagation as a promising but preliminary mechanism for monitoring Agentic RAG systems, with future validation required in industrial domains such as Offshore Wind (OSW) maintenance decision support.