Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning

• URL: http://arxiv.org/abs/2509.02401v1
• Date: Tue, 02 Sep 2025 15:12:10 GMT
• Title: Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning
• Abstract summary: Large language model (LLM) agents are increasingly deployed in structured biomedical data environments.<n>We introduce an uncertainty-aware agent for query-conditioned multi-table summarization.
• Score: 19.099363114326355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents are increasingly deployed in structured biomedical data environments, yet they often produce fluent but overconfident outputs when reasoning over complex multi-table data. We introduce an uncertainty-aware agent for query-conditioned multi-table summarization that leverages two complementary signals: (i) retrieval uncertainty--entropy over multiple table-selection rollouts--and (ii) summary uncertainty--combining self-consistency and perplexity. Summary uncertainty is incorporated into reinforcement learning (RL) with Group Relative Policy Optimization (GRPO), while both retrieval and summary uncertainty guide inference-time filtering and support the construction of higher-quality synthetic datasets. On multi-omics benchmarks, our approach improves factuality and calibration, nearly tripling correct and useful claims per summary (3.0\(\rightarrow\)8.4 internal; 3.6\(\rightarrow\)9.9 cancer multi-omics) and substantially improving downstream survival prediction (C-index 0.32\(\rightarrow\)0.63). These results demonstrate that uncertainty can serve as a control signal--enabling agents to abstain, communicate confidence, and become more reliable tools for complex structured-data environments.

Related papers

• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• Neural Conjugate Aggregation: Identifiable Unsupervised Multi-Sensor Regression under Heterogeneous Sensor Bias [0.0]
  We study regression-based data fusion under uncertainty, where multiple noisy and biased measurement sources are available but ground-truth labels are absent during training.<n>This setting arises in sensor networks, simulation ensembles, and scientific monitoring systems where supervision is costly or infeasible.<n>We propose the Neural Conjugate Aggregation Model (NCAM), a hierarchical Bayesian framework that combines neural networks with conjugate Gaussian inference for unsupervised multi-source fusion.
  arXiv  Detail & Related papers  (2026-06-20T19:30:21Z)
• Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning [63.24624171679711]
  Large language model (LLM)-based agents often make suboptimal tool-use decisions.<n>We propose TRUST, which incorporates uncertainty quantification into reward design as a repulsive force for maintaining uncertainty separation.
  arXiv  Detail & Related papers  (2026-06-05T07:08:34Z)
• PRA-PoE: Robust Multimodal Alzheimer's Diagnosis with Arbitrary Missing Modalities [9.014577470296013]
  Missing modalities are prevalent in real-world Alzheimer's disease (AD) assessment.<n>Existing approaches that rely on implicit imputation or modality synthesis often fail to explicitly model modality availability and uncertainty.<n>We propose Prototype-anchored Representation Alignment (PRA) and an Uncertainty-aware Product of Experts (UA-PoE) fusion mechanism.
  arXiv  Detail & Related papers  (2026-05-13T06:54:21Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Causal Reconstruction of Sentiment Signals from Sparse News Data [0.0]
  Sentiment signals derived from sparse news are commonly used in financial analysis and technology monitoring.<n>We present a three-stage pipeline that aggregates article-level scores onto a regular temporal grid.<n>We evaluate the consistency of reconstructed signals against stock-price data for a dataset of AI-related news titles.
  arXiv  Detail & Related papers  (2026-03-24T09:13:33Z)
• Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering [1.295312759062166]
  Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models incorporate external evidence in clinical decision support.<n>These systems iteratively retrieve curated domain knowledge and synthesize it into structured reports before answer selection.<n>Although such pipelines can improve performance, their impact on reliability under model variability remains unclear.
  arXiv  Detail & Related papers  (2026-03-06T13:31:54Z)
• ThreatFormer-IDS: Robust Transformer Intrusion Detection with Zero-Day Generalization and Explainable Attribution [0.0]
  Intrusion detection in IoT and industrial networks requires models that can detect rare attacks at low false-positive rates while remaining reliable under evolving traffic and limited labels.<n>We propose ThreatFormer- IDS, a Transformer-based sequence modeling framework that converts flow records into time-ordered windows and learns contextual representations for robust intrusion screening.<n>On the ToN IoT benchmark with chronological evaluation, ThreatFormer-IDS achieves AUCROC 0.994, AUC-PR 0.956, and Recall@1%FPR 0.910, outperforming strong tree-based and sequence baselines.
  arXiv  Detail & Related papers  (2026-02-26T23:20:42Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregation [5.905949608791961]
  This paper introduces a semantics-driven federated IDS framework that incorporates language-derived semantic supervision into federated optimization.<n>The framework achieves over 80% zero-shot detection accuracy on unseen attack patterns, improving zero-day discrimination by more than 10% compared to similarity-based baselines.
  arXiv  Detail & Related papers  (2026-01-30T16:38:05Z)
• Explainability of Complex AI Models with Correlation Impact Ratio [10.61008729196936]
  Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment.<n>We introduce ExCIR (Explainability through Correlation Impact Ratio), a theoretically grounded, simple, and reliable metric for explaining the contribution of input features to model outputs.<n>We demonstrate that ExCIR captures dependencies arising from correlated features through a lightweight single pass formulation.
  arXiv  Detail & Related papers  (2026-01-10T21:56:24Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models [24.72990207218907]
  Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation.<n>We investigate how in-context information influences model behavior and whether LLMs can identify their unreliable responses.
  arXiv  Detail & Related papers  (2025-08-11T16:12:36Z)
• Online Robust Multi-Agent Reinforcement Learning under Model Uncertainties [10.054572105379425]
  Well-trained multi-agent systems can fail when deployed in real-world environments.<n>DRMGs enhance system resilience by optimizing for worst-case performance over a defined set of environmental uncertainties.<n>This paper pioneers the study of online learning in DRMGs, where agents learn directly from environmental interactions without prior data.
  arXiv  Detail & Related papers  (2025-08-04T23:14:32Z)
• Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG [51.120170062795566]
  We propose Divide-Then-Align (DTA) to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary.<n>DTA balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.
  arXiv  Detail & Related papers  (2025-05-27T08:21:21Z)
• Geometric Median Matching for Robust k-Subset Selection from Noisy Data [75.86423267723728]
  We propose a novel k-subset selection strategy that leverages Geometric Median -- a robust estimator with an optimal breakdown point of 1/2.<n>Our method iteratively selects a k-subset such that the mean of the subset approximates the GM of the (potentially) noisy dataset, ensuring robustness even under arbitrary corruption.
  arXiv  Detail & Related papers  (2025-04-01T09:22:05Z)
• Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis [55.13545823385091]
  Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents.<n>In real-world applications, each agent may experience slightly different transition dynamics, leading to inherent model mismatches.<n>We show that even moderate levels of information sharing significantly mitigate environment-specific errors.
  arXiv  Detail & Related papers  (2025-03-21T18:06:28Z)
• Disentangling Uncertainties by Learning Compressed Data Representation [2.959687944707463]
  We propose a framework that learns a neural network encoding of the data distribution and enables direct sampling from the output distribution.<n>Our approach incorporates a novel inference procedure based on Langevin dynamics sampling, allowing CDRM to predict arbitrary output distributions.
  arXiv  Detail & Related papers  (2025-03-20T02:37:48Z)
• Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth [0.0]
  We introduce a new approach in which several advanced large language models produce and answer intricate, doctoral-level probability problems.<n>Our investigation focuses on how agreement among diverse models can signal the reliability of their outputs.
  arXiv  Detail & Related papers  (2025-02-28T06:20:52Z)
• Learning from Noisy Labels via Conditional Distributionally Robust Optimization [5.85767711644773]
  crowdsourcing has emerged as a practical solution for labeling large datasets. It presents a significant challenge in learning accurate models due to noisy labels from annotators with varying levels of expertise.
  arXiv  Detail & Related papers  (2024-11-26T05:03:26Z)
• UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation [93.38604803625294]
  We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) We use Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-03T17:39:38Z)
• 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)

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.