Cognitive Friction: A Decision-Theoretic Framework for Bounded Deliberation in Tool-Using Agents

• URL: http://arxiv.org/abs/2603.30031v3
• Date: Thu, 02 Apr 2026 16:42:15 GMT
• Title: Cognitive Friction: A Decision-Theoretic Framework for Bounded Deliberation in Tool-Using Agents
• Abstract summary: Unconstrained tool-using agents must decide which information source to query and act on.<n>We propose the Triadic Cognitive Architecture (TCA), a decision-theoretic framework that formalizes these failure modes via cognitive friction.<n>We validate TCA in two controlled environments designed to isolate stopping quality, action selection under congestion, and temporal urgency.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous tool-using agents in networked environments must decide which information source to query and when to stop querying and act. Without principled bounds on information-acquisition costs, unconstrained agents exhibit systematic failure modes: excessive tool use under congestion, prolonged deliberation under time decay, and brittle behavior under ambiguous evidence. We propose the Triadic Cognitive Architecture (TCA), a decision-theoretic framework that formalizes these failure modes via cognitive friction. By combining nonlinear filtering, congestion-dependent cost dynamics, and HJB optimal stopping, TCA models deliberation as stochastic control over a joint belief-congestion state, explicitly pricing information by tool signal quality and live network load. TCA yields an HJB-inspired stopping boundary and a computable rollout-based approximation of belief-dependent value-of-information with a net-utility halting condition. We validate TCA in two controlled environments (EMDG and NSTG) designed to isolate stopping quality, action selection under congestion, and temporal urgency. TCA improves resource outcomes while reducing time-to-action without degrading accuracy, gaining 36 viability points in EMDG and 33 integrity points in NSTG over greedy baselines. Ablations show that selection and stopping must be optimized jointly, as stopping rules alone recover at most 4 viability points. Sensitivity sweeps over alpha, beta, and lambda_S yield stable accuracy and interpretable trade-offs, and a continuation-value sweep over eta values 0, 0.1, 0.3, and 0.5 finds eta equal to zero is optimal under high temporal urgency. Finally, we demonstrate an illustrative instantiation around a black-box LLM on a memorisation-free corpus, where the same stopping principle executes using empirically computable uncertainty and value-of-information proxies.

Related papers

• DACRI: Decision-Aware Causal Intervention Ranking for Critical Supply Chains [7.300943403522602]
  We present CriticalSCM-Bench v1, a controlled synthetic benchmark with causal ground truth, paired factual/counterfactual rollouts, and an explicit net-value objective.<n>Relative to a full-information train-selected static benchmark, LambdaMART improves median normalized net value by 5.7--16.2%.<n>On digital infrastructure, a domain-informed constant-buffer policy remains stronger, showing that greater model complexity is not uniformly justified.
  arXiv  Detail & Related papers  (2026-08-11T17:12:08Z)
• Event-Structured Physics-Informed Neural Networks for Differentiable Critical Clearing Boundaries [4.920314418301607]
  Transient-stability assessment determines whether a power system can recover after a disturbance.<n>Key metric is the critical clearing time (CCT), which specifies the maximum time available to clear a fault before synchronism is lost.<n>We propose an event-structured physics-informed neural network (ES-PINN) that aligns its representation with the pre-fault, fault-on, and post-clearing swing dynamics.
  arXiv  Detail & Related papers  (2026-07-30T04:56:29Z)
• TimeLAVA: Learning-Agnostic Data Valuation for Time Series [48.76711740818533]
  TimeLAVA is a learning-agnostic framework that values temporal segments by their marginal contribution to minimize distributional discrepancy between evaluated and reference data.<n>We provide theoretical guarantees linking valuation to model-agnostic generalization and prove bounded sensitivity to contamination.
  arXiv  Detail & Related papers  (2026-06-17T06:16:16Z)
• Hybrid Robustness Verification for Spatio-Temporal Neural Networks [19.026662893450425]
  Existing verification methods rely on overly conservative approximations or incur prohibitive computational costs.<n>In practice, adversarial perturbations exhibit structured spatial and temporal correlations, constrained to lower-dimensional, semantically meaningful subspaces.<n>We study robustness verification 3D CNNs processing video inputs, targeting applications in action recognition (UCF-101), autonomous driving (Udacity), medical imaging (MedMNIST)
  arXiv  Detail & Related papers  (2026-06-08T17:06:51Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration [76.08899010904652]
  CapCal is a training-free framework that mechanically decouples positional bias from ranking decisions.<n>It achieves superior performance among training-free methods while preserving single-pass efficiency.
  arXiv  Detail & Related papers  (2026-04-11T10:47:22Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• Determinism in the Undetermined: Deterministic Output in Charge-Conserving Continuous-Time Neuromorphic Systems with Temporal Stochasticity [15.346559359976412]
  We develop a unified continuous-time framework for spiking neural networks (SNNs)<n>We prove that this mapping is strictly invariant to spike timing in acyclic networks.<n>We establish an exact representational correspondence between these charge-conserving SNNs and quantized artificial neural networks.
  arXiv  Detail & Related papers  (2026-03-16T23:00:04Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Adaptive Manipulation Potential and Haptic Estimation for Tool-Mediated Interaction [14.888648782445694]
  This paper introduces a parameterized Equilibrium Manifold (EM) as a unified representation for tool-mediated interaction.<n>We develop a closed-loop framework that integrates haptic estimation, online planning, and adaptive stiffness control.<n>The framework is validated through simulation and over 260 real-world screw-loosening trials.
  arXiv  Detail & Related papers  (2026-03-11T02:57:55Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• 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)
• Logic-Driven Semantic Communication for Resilient Multi-Agent Systems [26.964933264412412]
  6G networks are accelerating autonomy and intelligence in large-scale, decentralized multi-agent systems.<n>This article proposes a formal definition of MAS resilience grounded in two complementary dimensions.<n>We design an agent architecture and develop decentralized algorithms to achieve both epistemic and action resilience.
  arXiv  Detail & Related papers  (2026-01-11T00:54:09Z)
• TARDis: Time Attenuated Representation Disentanglement for Incomplete Multi-Modal Tumor Segmentation and Classification [10.329406702659123]
  Tumor segmentation and diagnosis in contrast-enhanced Computed Tomography (CT) rely heavily on the physiological dynamics of contrast agents.<n>Existing deep learning approaches typically treat missing phases as absent independent channels, ignoring the inherent temporal continuity of hemodynamics.<n>We propose Time Attenuated Representation Disentanglement (TARDis), a novel physics-aware framework that redefines missing modalities as missing sample points on a continuous Time-Attenuation Curve.
  arXiv  Detail & Related papers  (2025-12-04T08:44:50Z)
• A Mathematical Framework for AI Singularity: Conditions, Bounds, and Control of Recursive Improvement [1.932555230783329]
  We develop an analytic framework for self-improvement that links capability growth to resource build-out and deployment policies.<n>We derive decision rules that map observable series into yes/no certificates for runaway versus nonsingular behavior.<n>The framework yields falsifiable tests based on how fast improvement accelerates relative to its current level.
  arXiv  Detail & Related papers  (2025-11-08T21:25:38Z)
• T3former: Temporal Graph Classification with Topological Machine Learning [4.4924444466378555]
  Temporal graph classification plays a critical role in applications such as cybersecurity, brain connectivity analysis, and traffic monitoring.<n>We introduce T3former, a novel Topological Temporal Transformer that leverages sliding-window topological and spectral descriptors as first-class tokens, integrated via a specialized Descriptor-Attention mechanism.<n>T3former achieves state-of-the-art performance across multiple benchmarks, including dynamic social networks, brain functional connectivity datasets, and traffic networks.
  arXiv  Detail & Related papers  (2025-10-15T17:46:32Z)
• On the Identification of Temporally Causal Representation with Instantaneous Dependence [50.14432597910128]
  Temporally causal representation learning aims to identify the latent causal process from time series observations. Most methods require the assumption that the latent causal processes do not have instantaneous relations. We propose an textbfIDentification framework for instantanetextbfOus textbfLatent dynamics.
  arXiv  Detail & Related papers  (2024-05-24T08:08:05Z)
• TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling [54.97005925277638]
  The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. It remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. We propose a novel biologically inspired Two-Compartment Leaky Integrate-and-Fire spiking neuron model, dubbed TC-LIF.
  arXiv  Detail & Related papers  (2023-08-25T08:54:41Z)

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.