Uncertainty Propagation in LLM-Based Systems

• URL: http://arxiv.org/abs/2604.23505v1
• Date: Sun, 26 Apr 2026 02:48:03 GMT
• Title: Uncertainty Propagation in LLM-Based Systems
• Abstract summary: Uncertainty in large language model (LLM)-based systems is often studied at the level of a single model output.<n>This paper develops a systems-level account of uncertainty propagation.
• Score: 29.364057146424415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• The Anatomy of Uncertainty in LLMs [10.50144444577399]
  We advocate for an uncertainty decomposition framework that dissects uncertainty into three distinct semantic components.<n>Our framework provides a better understanding to audit LLM reliability and detect hallucinations, paving the way for targeted interventions and more trustworthy systems.
  arXiv  Detail & Related papers  (2026-03-26T02:59:40Z)
• Managing Uncertainty in LLM-based Multi-Agent System Operation [4.565220771764574]
  We propose a lifecycle-based uncertainty management framework for safety-critical multi-agent software systems.<n>We demonstrate the feasibility of the framework using a real-world LLM-based multi-agent echocardiographic software system developed in clinical collaboration.
  arXiv  Detail & Related papers  (2026-02-26T13:49:16Z)
• PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling [47.029742241618635]
  Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simulation.<n>We propose PhysicsAgentABM, which shifts inference to behaviorally coherent agent clusters.<n> Experiments across public health, finance, and social sciences show consistent gains in event-time accuracy and calibration over mechanistic, neural, and LLM baselines.
  arXiv  Detail & Related papers  (2026-02-05T18:59:01Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions [0.0]
  This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models interact with each other.<n>We propose a conceptual transition from model-level safety to system-level safety, introducing the framework of the Emergent Systemic Risk Horizon (ESRH)<n>The paper contributes (i) a theoretical account of collective risk in interacting LLMs, (ii) a taxonomy connecting micro, meso, and macro-level failure modes, and (iii) a design proposal for InstitutionalAI, an architecture for embedding adaptive oversight within multi-agent systems.
  arXiv  Detail & Related papers  (2025-12-02T12:06:57Z)
• Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey [69.45421620616486]
  This work presents the first structured taxonomy and analysis of discrete tokenization methods designed for large language models (LLMs)<n>We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines.<n>We identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints.
  arXiv  Detail & Related papers  (2025-07-21T10:52:14Z)
• A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [93.8285345915925]
  Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making.<n>With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems.<n>We categorize existing methods along two dimensions: (1) Regimes, which define the stage at which reasoning is achieved; and (2) Architectures, which determine the components involved in the reasoning process.
  arXiv  Detail & Related papers  (2025-04-12T01:27:49Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Supporting Early-Safety Analysis of IoT Systems by Exploiting Testing Techniques [9.095386349136717]
  FailureLogic Analysis FLA is a technique that helps predict potential failure scenarios. manually specifying FLA rules can be arduous and errorprone leading to incomplete or inaccurate specifications. We propose adopting testing methodologies to improve the completeness and correctness of these rules.
  arXiv  Detail & Related papers  (2023-09-06T13:32:39Z)
• Safe Multi-agent Learning via Trapping Regions [89.24858306636816]
  We apply the concept of trapping regions, known from qualitative theory of dynamical systems, to create safety sets in the joint strategy space for decentralized learning. We propose a binary partitioning algorithm for verification that candidate sets form trapping regions in systems with known learning dynamics, and a sampling algorithm for scenarios where learning dynamics are not known.
  arXiv  Detail & Related papers  (2023-02-27T14:47:52Z)
• STPA for Learning-Enabled Systems: A Survey and A New Practice [12.665507596261266]
  Systems Theoretic Process Analysis (STPA) is a systematic approach for hazard analysis that has been used across many industrial sectors including transportation, energy, and defense. The trend of using Machine Learning (ML) in safety-critical systems has led to the need of extendingSTPA to Learning-Enabled Systems (LESs) We present a systematic survey of 31 papers, summarising them from five perspectives (attributes of concern, objects under study, modifications, derivatives and processes being modelled) We introduce DeepSTPA, which enhances DeepSTPA from two aspects that are missing from the state-of-the-
  arXiv  Detail & Related papers  (2023-02-21T10:43:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.