Cover Image

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khan, Rafflesia, Khan, Nafiul Islam
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Gossip-Enhanced Communication Substrate for Agentic AI: Toward Decentralized Coordination in Large-Scale Multi-Agent Systems
by: Khan, Nafiul I., et al.
Published: (2025)

First-of-its-kind AI model for bioacoustic detection using a lightweight associative memory Hopfield neural network
by: Gascoyne, Andrew, et al.
Published: (2025)

TiledAttention: a CUDA Tile SDPA Kernel for PyTorch
by: Khan, Taimur
Published: (2026)

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
by: Liu, Jiashun, et al.
Published: (2025)

DiPT: Enhancing LLM reasoning through diversified perspective-taking
by: Just, Hoang Anh, et al.
Published: (2024)

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
by: Leong, Jun Wen
Published: (2026)

LLM+KG@VLDB'24 Workshop Summary
by: Khan, Arijit, et al.
Published: (2024)

DeepFeatIoT: Unifying Deep Learned, Randomized, and LLM Features for Enhanced IoT Time Series Sensor Data Classification in Smart Industries
by: Inan, Muhammad Sakib Khan, et al.
Published: (2025)

GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support
by: Sheikh, Muhammad Umer, et al.
Published: (2026)

AmpliNetECG12: A lightweight SoftMax-based relativistic amplitude amplification architecture for 12 lead ECG classification
by: Srivastava, Shreya
Published: (2024)

Revisiting Gossip Protocols: A Vision for Emergent Coordination in Agentic Multi-Agent Systems
by: Habiba, Mansura, et al.
Published: (2025)

When LLMs get significantly worse: A statistical approach to detect model degradations
by: Kübler, Jonas, et al.
Published: (2026)

Forager: a lightweight testbed for continual learning with partial observability in RL
by: Tang, Steven, et al.
Published: (2026)

Is Monotonic Sampling Necessary in Diffusion Models?
by: Khan, Muhammad Haris
Published: (2026)

Knowledge Adaptation as Posterior Correction
by: Khan, Mohammad Emtiyaz
Published: (2025)

Information Geometry of Variational Bayes
by: Khan, Mohammad Emtiyaz
Published: (2025)

Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
by: Liu, Tianming, et al.
Published: (2025)

Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
by: Su, Xuerui, et al.
Published: (2025)

Performance of AI agents based on reasoning language models on ALD process optimization tasks
by: Yanguas-Gil, Angel
Published: (2026)

Progressive Size-Adaptive Federated Learning: A Comprehensive Framework for Heterogeneous Multi-Modal Data Systems
by: Hussain, Sajid, et al.
Published: (2025)

Towards Trustworthy Keylogger detection: A Comprehensive Analysis of Ensemble Techniques and Feature Selections through Explainable AI
by: Mahmud, Monirul Islam
Published: (2025)

Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling
by: Cheshmi, Seyyed Saeid, et al.
Published: (2025)

Self-rewarding correction for mathematical reasoning
by: Xiong, Wei, et al.
Published: (2025)

UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs
by: Neth, Ashe, et al.
Published: (2025)

Federated Proximal Optimization for Privacy-Preserving Heart Disease Prediction: A Controlled Simulation Study on Non-IID Clinical Data
by: Asad, Farzam, et al.
Published: (2026)

S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
by: Khan, Sajjad
Published: (2026)

From Literal to Liberal: A Meta-Prompting Framework for Eliciting Human-Aligned Exception Handling in Large Language Models
by: Khan, Imran
Published: (2025)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
by: Khan, Imran
Published: (2025)

Adaptive Opponent Policy Detection in Multi-Agent MDPs: Real-Time Strategy Switch Identification Using Running Error Estimation
by: Mridul, Mohidul Haque, et al.
Published: (2024)

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
by: Mirtaheri, Parsa, et al.
Published: (2026)

Dynamic Logistic Ensembles with Recursive Probability and Automatic Subset Splitting for Enhanced Binary Classification
by: Khan, Mohammad Zubair, et al.
Published: (2024)

Reinforcing privacy reasoning in LLMs via normative simulacra from fiction
by: Franchi, Matt, et al.
Published: (2026)

Outlier detection in maritime environments using AIS data and deep recurrent architectures
by: Maganaris, Constantine, et al.
Published: (2024)

Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget
by: Khan, Zohaib, et al.
Published: (2026)

ProvMind: Provenance-grounded reasoning for materials synthesis
by: Zhang, Yiming, et al.
Published: (2026)

Reinforcement Learning in hyperbolic space for multi-step reasoning
by: Xu, Tao, et al.
Published: (2025)

A lightweight Spatial-Temporal Graph Neural Network for Long-term Time Series Forecasting
by: Moges, Henok Tenaw, et al.
Published: (2025)

Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt
by: de Mijolla, Damien, et al.
Published: (2024)

ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs
by: Shinwari, Haseeb Ullah Khan, et al.
Published: (2025)

Optimal Kernel Tuning Parameter Prediction using Deep Sequence Models
by: Mahmood, Khawir, et al.
Published: (2024)