Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier

• URL: http://arxiv.org/abs/2606.20662v1
• Date: Tue, 09 Jun 2026 23:13:53 GMT
• Title: Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier
• Abstract summary: We argue that uncertainty does not propagate simply because a trajectory contains uncertain steps; it propagates only when it survives the handoff between components.<n>We propose latent uncertainty as an uncertainty-bearing carrier attached to decision handoffs.
• Score: 19.977378656876645
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern agent systems can turn uncertainty into overconfidence. Fragile upstream decisions are often exposed to downstream components as clean intermediate artifacts, while the uncertainty behind those decisions is lost at the interface. As a result, local ambiguity can become system-level error amplification. We argue that this reveals an interface bottleneck in agent uncertainty propagation: uncertainty does not propagate simply because a trajectory contains uncertain steps; it propagates only when it survives the handoff between components. We define uncertain decision handoff as the transfer of an intermediate decision made under uncertainty, and identify confidence laundering as a failure mode in which fragile upstream states are repackaged as procedurally valid artifacts that downstream agents over-trust. To address this bottleneck, we propose latent uncertainty as an uncertainty-bearing carrier attached to decision handoffs. Rather than replacing text with hidden states, latent uncertainty aims to preserve pre-commitment fragility in a form that downstream components can use. This position shifts agent uncertainty propagation from step-wise uncertainty estimation toward uncertainty-preserving interface design for more recoverable agent systems.

Related papers

• ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generation [7.5571037918649155]
  Variational autoencoders generate samples from probabilistic latent representations but do not distinguish uncertainty about the latent location from variability around it.<n>We formulate ELVAE, an evidential learning-based VAE in which each latent coordinate is governed by an input-dependent normal-inverse-gamma posterior.<n>Low-uncertainty anchors support more reliable synthetic samples, while high-uncertainty anchors can be deliberately exploited for stress testing.
  arXiv  Detail & Related papers  (2026-08-11T02:45:59Z)
• A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies [2.854451361373021]
  We propose a unified definition of uncertainty as pointwise posterior risk, the expected loss of a predictor under the distribution of plausible ground-truth functions.<n>This view combines Bayesian uncertainty over functions with estimator-dependent deviations from the posterior mean, capturing effects such as misspecification and optimization error.<n>By avoiding proxy evaluations, the benchmark enables fine-grained analysis of uncertainty estimates.
  arXiv  Detail & Related papers  (2026-08-06T13:05:16Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Decision Making Needs Uncertainty Quantification [Lecture Notes] [35.36148913066079]
  This lecture note develops, from first principles and within a single decision-theoretic setting, the link between the objective and the knowledge of an agent.<n>We show that a risk-neutral agent needs the posterior distribution over the state, whereas a risk-averse agent can rely without loss of optimality on a prediction set and a worst-case decision rule.
  arXiv  Detail & Related papers  (2026-07-15T22:50:26Z)
• Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities [13.14855346396444]
  First-order uncertainty captures uncertainty over possible responses to a prompt, while second-order uncertainty quantifies indeterminacy in the underlying probability model itself.<n>We introduce general-purpose prompting and post-processing procedures to directly elicit and quantify both orders of uncertainty, and demonstrate their effectiveness across diverse settings.
  arXiv  Detail & Related papers  (2026-03-11T04:21:04Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning [1.2183405753834562]
  This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of machine learning (ML) systems.<n>We first show that a model's training trajectory contains rich uncertainty signals that can be exploited without altering its architecture or loss.<n>We propose a lightweight, post-hoc abstention method that works across tasks, avoids the cost of deep ensembles, and achieves state-of-the-art selective prediction performance.
  arXiv  Detail & Related papers  (2025-08-11T02:33:53Z)
• Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving? [9.729293160819038]
  We investigate how an agent's behavior is influenced by an uncertain perception.<n>We introduce uncertainty in the observation space by perturbing the perception of the given agent.<n>Our experiments show that an unreliable observation space modeled by a perturbed perception leads to a defensive driving behavior of the agent.
  arXiv  Detail & Related papers  (2025-02-17T14:56:25Z)
• Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching [61.73532883992135]
  We propose a new uncertainty-aware stereo matching framework.<n>We adopt Bayes risk as the measurement of uncertainty and use it to separately estimate data and model uncertainty.
  arXiv  Detail & Related papers  (2024-12-24T23:28:20Z)
• SAUP: Situation Awareness Uncertainty Propagation on LLM Agent [52.444674213316574]
  Large language models (LLMs) integrated into multistep agent systems enable complex decision-making processes across various applications.<n>Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multistep decision-making process and the dynamic interactions between agents and their environments.<n>We propose SAUP, a novel framework that propagates uncertainty through each step of an LLM-based agent's reasoning process.
  arXiv  Detail & Related papers  (2024-12-02T01:31:13Z)
• Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
  We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
  arXiv  Detail & Related papers  (2024-09-26T21:00:45Z)
• Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving [1.6758573326215689]
  Reinforcement learning can be used to create a decision-making agent for autonomous driving. Previous approaches provide only black-box solutions, which do not offer information on how confident the agent is about its decisions. This paper introduces the Ensemble Quantile Networks (EQN) method, which combines distributional RL with an ensemble approach to obtain a complete uncertainty estimate.
  arXiv  Detail & Related papers  (2021-05-21T10:36:16Z)
• Temporal Difference Uncertainties as a Signal for Exploration [76.6341354269013]
  An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy. In this paper, we highlight that value estimates are easily biased and temporally inconsistent. We propose a novel method for estimating uncertainty over the value function that relies on inducing a distribution over temporal difference errors.
  arXiv  Detail & Related papers  (2020-10-05T18:11:22Z)
• Localization Uncertainty Estimation for Anchor-Free Object Detection [48.931731695431374]
  There are several limitations of the existing uncertainty estimation methods for anchor-based object detection. We propose a new localization uncertainty estimation method called UAD for anchor-free object detection. Our method captures the uncertainty in four directions of box offsets that are homogeneous, so that it can tell which direction is uncertain.
  arXiv  Detail & Related papers  (2020-06-28T13:49:30Z)

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.