Cover Image

Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shakya, Srijan, Hartl, Anamaria-Roberta, Hochreiter, Sepp, Pöppel, Korbinian
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 62M45
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Point Process Model for Optimizing Repeated Personalized Action Delivery to Users
by: Merkov, Alexander, et al.
Published: (2025)

Leveraging Non-Decimated Wavelet Packet Features and Transformer Models for Time Series Forecasting
by: Nason, Guy P, et al.
Published: (2024)

Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference
by: Wang, Zheyu Oliver, et al.
Published: (2023)

Measuring Neural Network Complexity via Effective Degrees of Freedom
by: Zhou, Jia, et al.
Published: (2026)

Custom Loss Functions in Fuel Moisture Modeling
by: Hirschi, Jonathon
Published: (2025)

Revisiting semi-supervised training objectives for differentiable particle filters
by: Li, Jiaxi, et al.
Published: (2024)

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
by: Pöppel, Korbinian, et al.
Published: (2024)

Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths
by: Zhao, Yuzhen, et al.
Published: (2025)

Using Artificial Neural Networks to Predict Claim Duration in a Work Injury Compensation Environment
by: Almudevar, Anthony
Published: (2026)

Generalization error bounds for two-layer neural networks with Lipschitz loss function
by: Nguwi, Jiang Yu, et al.
Published: (2026)

Random Vector Functional Link Networks for Function Approximation on Manifolds
by: Needell, Deanna, et al.
Published: (2020)

The Predictive-Causal Gap: An Impossibility Theorem and Large-Scale Neural Evidence
by: Liu, Kejun
Published: (2026)

Universal Adaptive Environment Discovery
by: Matymov, Madi, et al.
Published: (2025)

Critical Points of Random Neural Networks
by: Di Lillo, Simmaco
Published: (2025)

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
by: Beck, Maximilian, et al.
Published: (2025)

A Complete Symmetry Classification of Shallow ReLU Networks
by: Ramakrishnan, Pranavkrishnan
Published: (2026)

Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free
by: Zhang, Stephen Y., et al.
Published: (2025)

Sharp Bounds on the Approximation Rates, Metric Entropy, and $n$-widths of Shallow Neural Networks
by: Siegel, Jonathan W., et al.
Published: (2021)

Fractal and Regular Geometry of Deep Neural Networks
by: Di Lillo, Simmaco, et al.
Published: (2025)

Log-Gaussian Gamma Processes for Training Bayesian Neural Networks in Raman and CARS Spectroscopies
by: Härkönen, Teemu, et al.
Published: (2023)

A Distribution-to-Distribution Neural Probabilistic Forecasting Framework for Dynamical Systems
by: Yang, Tianlin, et al.
Published: (2026)

Designing Time-Series Models With Hypernetworks & Adversarial Portfolios
by: Staněk, Filip
Published: (2024)

ASNN: Learning to Suggest Neural Architectures from Performance Distributions
by: Hong, Jinwook
Published: (2025)

Towards an Algebraic Framework For Approximating Functions Using Neural Network Polynomials
by: Rafi, Shakil, et al.
Published: (2024)

From Theory to Application: A Practical Introduction to Neural Operators in Scientific Computing
by: Jha, Prashant K.
Published: (2025)

pLSTM: parallelizable Linear Source Transition Mark networks
by: Pöppel, Korbinian, et al.
Published: (2025)

Optimizing Data Augmentation through Bayesian Model Selection
by: Matymov, Madi, et al.
Published: (2025)

Efficient reconstruction of multidimensional random field models with heterogeneous data using stochastic neural networks
by: Xia, Mingtao, et al.
Published: (2025)

Efficient Time-Series Approximation with Linear Recurrent Neural Networks: Architecture Learning and Predictive Power
by: Stolzenburg, Frieder, et al.
Published: (2018)

Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samples
by: Dai, Yufang, et al.
Published: (2026)

Minimaxity and Admissibility of Bayesian Neural Networks
by: Coulson, Daniel Andrew, et al.
Published: (2026)

In almost all shallow analytic neural network optimization landscapes, efficient minimizers have strongly convex neighborhoods
by: Benning, Felix, et al.
Published: (2025)

Adaptive deep density approximation for stochastic dynamical systems
by: He, Junjie, et al.
Published: (2024)

Approximation Rates for Shallow ReLU$^k$ Neural Networks on Sobolev Spaces via the Radon Transform
by: Mao, Tong, et al.
Published: (2024)

Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces
by: Siegel, Jonathan W.
Published: (2022)

Vision-LSTM: xLSTM as Generic Vision Backbone
by: Alkin, Benedikt, et al.
Published: (2024)

Generalization and Feature Attribution in Machine Learning Models for Crop Yield and Anomaly Prediction in Germany
by: Baatz, Roland
Published: (2025)

Global $\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning
by: Chen, Thomas
Published: (2023)

Architecture independent generalization bounds for overparametrized deep ReLU networks
by: Bapu, Anandatheertha, et al.
Published: (2025)

Zero loss guarantees and explicit minimizers for generic overparametrized Deep Learning networks
by: Chen, Thomas, et al.
Published: (2025)