Image de couverture de livre

Provable Benefits of In-Tool Learning for Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Houliston, Sam, Odonnat, Ambroise, Arnal, Charles, Cabannes, Vivien
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Touring sampling with pushforward maps
par: Cabannes, Vivien, et autres
Publié: (2023)

Clustering Head: A Visual Case Study of the Training Dynamics in Transformers
par: Odonnat, Ambroise, et autres
Publié: (2024)

Learning with Hidden Factorial Structure
par: Arnal, Charles, et autres
Publié: (2024)

Easing Optimization Paths: a Circuit Perspective
par: Odonnat, Ambroise, et autres
Publié: (2025)

Optimal Self-Consistency for Efficient Reasoning with Large Language Models
par: Feng, Austin, et autres
Publié: (2025)

Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
par: Odonnat, Ambroise, et autres
Publié: (2023)

The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
par: Cabannes, Vivien, et autres
Publié: (2023)

Large Language Models as Markov Chains
par: Zekri, Oussama, et autres
Publié: (2024)

Learning Associative Memories with Gradient Descent
par: Cabannes, Vivien, et autres
Publié: (2024)

Iteration Head: A Mechanistic Study of Chain-of-Thought
par: Cabannes, Vivien, et autres
Publié: (2024)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
par: Gaitonde, Jason, et autres
Publié: (2026)

Provable Benefit of Cutout and CutMix for Feature Learning
par: Oh, Junsoo, et autres
Publié: (2024)

Mode Estimation with Partial Feedback
par: Arnal, Charles, et autres
Publié: (2024)

CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data
par: Xie, Shifeng, et autres
Publié: (2025)

Provable Training Data Identification for Large Language Models
par: Liu, Zhenlong, et autres
Publié: (2025)

Efficient RL Training for LLMs with Experience Replay
par: Arnal, Charles, et autres
Publié: (2026)

Provable Long-Range Benefits of Next-Token Prediction
par: Cao, Xinyuan, et autres
Publié: (2025)

Uncertainty-Penalized Direct Preference Optimization
par: Houliston, Sam, et autres
Publié: (2024)

Scaling Laws for Associative Memories
par: Cabannes, Vivien, et autres
Publié: (2023)

Vision Transformer Finetuning Benefits from Non-Smooth Components
par: Odonnat, Ambroise, et autres
Publié: (2026)

Provable Benefit of Sign Descent: A Minimal Model Under Heavy-Tailed Class Imbalance
par: Yadav, Robin, et autres
Publié: (2025)

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities
par: Lalou, Yanis, et autres
Publié: (2024)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
par: Kim, Juno, et autres
Publié: (2025)

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
par: Arnal, Charles, et autres
Publié: (2025)

Provable Benefits of Complex Parameterizations for Structured State Space Models
par: Ran-Milo, Yuval, et autres
Publié: (2024)

Provably Robust Adaptation for Language-Empowered Foundation Models
par: Lai, Yuni, et autres
Publié: (2025)

Provable Scaling Laws for the Test-Time Compute of Large Language Models
par: Chen, Yanxi, et autres
Publié: (2024)

Automatic Textbook Formalization
par: Gloeckle, Fabian, et autres
Publié: (2026)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
par: Banerjee, Arko, et autres
Publié: (2024)

Large Language Models as Tool Makers
par: Cai, Tianle, et autres
Publié: (2023)

Aligning Agents like Large Language Models
par: Jelley, Adam, et autres
Publié: (2024)

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
par: Zhang, Yuanhe, et autres
Publié: (2025)

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
par: Huang, Wei, et autres
Publié: (2026)

OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models
par: Zhang, Jianzhang, et autres
Publié: (2025)

A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services
par: Pan, Guanzhong, et autres
Publié: (2025)

AGENT: An Aerial Vehicle Generation and Design Tool Using Large Language Models
par: Samplawski, Colin, et autres
Publié: (2025)

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
par: Wu, Duo, et autres
Publié: (2024)

Explaining Machine Learning Predictive Models through Conditional Expectation Methods
par: Ruiz-España, Silvia, et autres
Publié: (2026)

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent
par: Chen, Bo, et autres
Publié: (2025)

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
par: Van Assel, Hugues, et autres
Publié: (2025)