# Uncertainty Propagation in LLM-Based Systems

arXiv: https://arxiv.org/abs/2604.23505 · HTML: https://mlsanity.com/paper/2604.23505/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 95 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 30 of 45)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Cognitive Mirage: A Review of Hallucinations in Large Language Models](https://mlsanity.com/paper/2309.06794/) (2023)
- [Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown](https://mlsanity.com/paper/2410.00847/) (2024)
- [A Survey of Uncertainty Estimation Methods on Large Language Models](https://mlsanity.com/paper/2503.00172/) (2025)
- [A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice](https://mlsanity.com/paper/2410.15326/) (2024)
- [Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.23352/) (2025)
- [UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making](https://mlsanity.com/paper/2506.17419/) (2025)
- [Structured Uncertainty guided Clarification for LLM Agents](https://mlsanity.com/paper/2511.08798/) (2025)
- [Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs](https://mlsanity.com/paper/2503.15341/) (2025)
- [How to Correctly Report LLM-as-a-Judge Evaluations](https://mlsanity.com/paper/2511.21140/) (2025)
- [ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction](https://mlsanity.com/paper/2508.00500/) (2025)
- [BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design](https://mlsanity.com/paper/2508.21184/) (2025)
- [CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought](https://mlsanity.com/paper/2502.17214/) (2025)
- [Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies](https://mlsanity.com/paper/2512.19673/) (2025)
- [UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.02719/) (2024)
- [Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads](https://mlsanity.com/paper/2505.20045/) (2025)
- [Agentic Confidence Calibration](https://mlsanity.com/paper/2601.15778/) (2026)
- [DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics](https://mlsanity.com/paper/2407.06426/) (2024)
- [Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis](https://mlsanity.com/paper/2505.07459/) (2025)
- [Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits](https://mlsanity.com/paper/2512.20578/) (2025)
- [SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows](https://mlsanity.com/paper/2508.07935/) (2025)
- [Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs](https://mlsanity.com/paper/2509.13813/) (2025)
- [Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models](https://mlsanity.com/paper/2505.24187/) (2025)

## Built on by (most cited first, 3 of 3)

- [Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents](https://mlsanity.com/paper/2606.20631/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)
- [Verbalized and Internal Probabilities Are Coupled in Large Language Models](https://mlsanity.com/paper/2610.00827/) (2026)

## Abstract (arXiv)

Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output, yet deployed LLM applications are compound systems in which uncertainty is transformed and reused across model internals, workflow stages, component boundaries, persistent state, and human or organisational processes. Without principled treatment of how uncertainty is carried and reused across these boundaries, early errors can propagate and compound in ways that are difficult to detect and govern. This paper develops a systems-level account of uncertainty propagation. It introduces a conceptual framing for characterising propagated uncertainty signals, presents a structured taxonomy spanning intra-model (P1), system-level (P2), and socio-technical (P3) propagation mechanisms, synthesises cross-cutting engineering insights, and identifies five open research challenges.