Imagen de Portada

Workspace Optimization: How to Train Your Agent

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sarafian, Elad, Kaplun, Gal, Banner, Ron, Soudry, Daniel, Ginsburg, Boris
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Normalized Architectures are Natively 4-Bit
por: Fishman, Maxim, et al.
Publicado: (2026)

FP4 All the Way: Fully Quantized Training of LLMs
por: Chmiel, Brian, et al.
Publicado: (2025)

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
por: Chmiel, Brian, et al.
Publicado: (2022)

Scaling FP8 training to trillion-token LLMs
por: Fishman, Maxim, et al.
Publicado: (2024)

Retrieval from Within: An Intrinsic Capability of Attention-Based Models
por: Hoffer, Elad, et al.
Publicado: (2026)

Optimistic Gradient Learning with Hessian Corrections for High-Dimensional Black-Box Optimization
por: Kfir, Yedidya, et al.
Publicado: (2025)

Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
por: Chmiel, Brian, et al.
Publicado: (2021)

How to Train Your LLM Web Agent: A Statistical Diagnosis
por: Vattikonda, Dheeraj, et al.
Publicado: (2025)

Does Your Optimizer Care How You Normalize? Normalization-Optimizer Coupling in LLM Training
por: Abouzeid, Abdelrahman
Publicado: (2026)

Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
por: Tang, Zirui, et al.
Publicado: (2026)

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
por: Blumenfeld, Yaniv, et al.
Publicado: (2024)

Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
por: Winston, Caleb, et al.
Publicado: (2026)

IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems
por: Levi, Elad, et al.
Publicado: (2025)

Star Attention: Efficient LLM Inference over Long Sequences
por: Acharya, Shantanu, et al.
Publicado: (2024)

EXAQ: Exponent Aware Quantization For LLMs Acceleration
por: Shkolnik, Moran, et al.
Publicado: (2024)

nGPT: Normalized Transformer with Representation Learning on the Hypersphere
por: Loshchilov, Ilya, et al.
Publicado: (2024)

SILO: Solving Inverse Problems with Latent Operators
por: Raphaeli, Ron, et al.
Publicado: (2025)

BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate
por: Mazza, Arnon, et al.
Publicado: (2026)

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
por: Qiao, Dan, et al.
Publicado: (2024)

Group-in-Group Policy Optimization for LLM Agent Training
por: Feng, Lang, et al.
Publicado: (2025)

GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory
por: Wu, Haoze, et al.
Publicado: (2024)

How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
por: Asawa, Parth, et al.
Publicado: (2025)

How Memory in Optimization Algorithms Implicitly Modifies the Loss
por: Cattaneo, Matias D., et al.
Publicado: (2025)

Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
por: Balaji, Vignesh, et al.
Publicado: (2025)

How to Turn Your Knowledge Graph Embeddings into Generative Models
por: Loconte, Lorenzo, et al.
Publicado: (2023)

No Need to Train Your RDB Foundation Model
por: Xu, Linjie, et al.
Publicado: (2026)

Tree Search-Based Policy Optimization under Stochastic Execution Delay
por: Valensi, David, et al.
Publicado: (2024)

Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning
por: Ficek, Aleksander, et al.
Publicado: (2025)

More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
por: Dalal, Gal, et al.
Publicado: (2026)

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
por: Plyusov, Daniil, et al.
Publicado: (2026)

Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement Learning
por: Maytié, Léopold, et al.
Publicado: (2025)

How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs
por: Estornell, Andrew, et al.
Publicado: (2025)

Research Program: Theory of Learning in Dynamical Systems
por: Hazan, Elad, et al.
Publicado: (2025)

Feed-Forward Optimization With Delayed Feedback for Neural Network Training
por: Flügel, Katharina, et al.
Publicado: (2023)

Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
por: Choudhury, Sanjiban, et al.
Publicado: (2024)

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
por: Huang, Jerry Y., et al.
Publicado: (2026)

Policy Gradient with Tree Expansion
por: Dalal, Gal, et al.
Publicado: (2023)

Agent Lightning: Train ANY AI Agents with Reinforcement Learning
por: Luo, Xufang, et al.
Publicado: (2025)

Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
por: Liu, Ning, et al.
Publicado: (2026)

Training Agents to Self-Report Misbehavior
por: Lee, Bruce W., et al.
Publicado: (2026)