mlsanityData to 14 Oct 2026

Uncertainty Propagation in LLM-Based Systems

arXiv 2604.23505 ↗First posted 26 Apr 2026cs.SE cs.AIcited by 3

Not on the map. Why?

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.

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

45 of 95 references.

References · 45

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2024Understanding the planning of LLM agents: A surveycited by 421
  3. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  4. 2025Why Language Models Hallucinatecited by 220
  5. 2025Deep Think with Confidencecited by 205
  6. 2025Where LLM Agents Fail and How They can Learn From Failurescited by 133
  7. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 130
  8. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 116
  9. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 84
  10. 2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknowncited by 74
  11. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 62
  12. 2024A Survey of Uncertainty Estimation in LLMs: Theory Meets Practicecited by 55
33 more
  1. 2025Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systemscited by 43
  2. 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 42
  3. 2025Structured Uncertainty guided Clarification for LLM Agentscited by 41
  4. 2025Uncertainty-Guided Chain-of-Thought for Code Generation with LLMscited by 32
  5. 2025How to Correctly Report LLM-as-a-Judge Evaluationscited by 30
  6. 2025ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Predictioncited by 28
  7. 2025BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Designcited by 24
  8. 2025CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thoughtcited by 23
  9. 2025Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policiescited by 23
  10. 2024UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generationcited by 16
  11. 2025Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Headscited by 16
  12. 2026Agentic Confidence Calibrationcited by 15
  13. 2024DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metricscited by 14
  14. 2025Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysiscited by 14
  15. 2025Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuitscited by 14
  16. 2025SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflowscited by 13
  17. 2025Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMscited by 13
  18. 2025Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Modelscited by 12
  19. 2025Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directionscited by 11
  20. 2025Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamicscited by 11
  21. 2025Rational Tuning of LLM Cascades via Probabilistic Modelingcited by 10
  22. 2025Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Ratecited by 10
  23. 2025Numerical stability analysis of large language modelscited by 9
  24. 2025Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Toolscited by 9
  25. 2025LLM Output Drift: Cross-Provider Validation & Mitigation for Financial Workflowscited by 7
  26. 2026When to Trust the Cheap Check: Weak and Strong Verification for Reasoningcited by 7
  27. 2025From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systemscited by 6
  28. 2025Zero-Overhead Introspection for Adaptive Test-Time Computecited by 6
  29. 2026A Structured Approach to Safety Case Construction for AI Systemscited by 6
  30. 2025Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Modelscited by 5
  31. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 4
  32. 2025RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detectioncited by 4
  33. 2025Robust Search with Uncertainty-Aware Value Models for Language Model Reasoningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agentscited by 1
  2. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Studycited by 0
  3. 2026Verbalized and Internal Probabilities Are Coupled in Large Language Modelscited by 0