Copertina

Revisiting DAgger in the Era of LLM-Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Changhao, Qiang, Rushi, Huang, Jiawei, Gao, Chenxiao, Zhang, Chao, He, Niao, Dai, Bo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploration-Driven Optimization for Test-Time Large Language Model Reasoning
di: Li, Changhao, et al.
Pubblicazione: (2026)

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
di: Li, Changhao, et al.
Pubblicazione: (2024)

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
di: Qiang, Rushi, et al.
Pubblicazione: (2025)

Robust Knowledge Transfer in Tiered Reinforcement Learning
di: Huang, Jiawei, et al.
Pubblicazione: (2023)

Steering No-Regret Agents in MFGs under Model Uncertainty
di: Widmer, Leo, et al.
Pubblicazione: (2025)

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
di: Huang, Jiawei, et al.
Pubblicazione: (2024)

MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline
di: Qiang, Rushi, et al.
Pubblicazione: (2025)

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
di: Huang, Jiawei, et al.
Pubblicazione: (2023)

HYDRA: Model Factorization Framework for Black-Box LLM Personalization
di: Zhuang, Yuchen, et al.
Pubblicazione: (2024)

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
di: Huang, Jiawei, et al.
Pubblicazione: (2025)

Data-Efficient Multitask DAgger
di: Fu, Haotian, et al.
Pubblicazione: (2025)

Learning to Steer Markovian Agents under Model Uncertainty
di: Huang, Jiawei, et al.
Pubblicazione: (2024)

FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies
di: Gao, Chenxiao, et al.
Pubblicazione: (2026)

Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
di: Li, Bingcong, et al.
Pubblicazione: (2024)

Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning
di: Yardim, Batuhan, et al.
Pubblicazione: (2024)

BiLoRA: A Bi-level Optimization Framework for Overfitting-Resilient Low-Rank Adaptation of Large Pre-trained Models
di: Qiang, Rushi, et al.
Pubblicazione: (2024)

MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts
di: Sun, Xiatao, et al.
Pubblicazione: (2023)

Spectral Representation-based Reinforcement Learning
di: Gao, Chenxiao, et al.
Pubblicazione: (2025)

AmorLIP: Efficient Language-Image Pretraining via Amortization
di: Sun, Haotian, et al.
Pubblicazione: (2025)

Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior
di: Yan, Mingyuan, et al.
Pubblicazione: (2024)

Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
di: Zhao, Anhao, et al.
Pubblicazione: (2026)

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
di: Zhang, Jiawei, et al.
Pubblicazione: (2025)

Primal Methods for Variational Inequality Problems with Functional Constraints
di: Zhang, Liang, et al.
Pubblicazione: (2024)

TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
di: Li, Xiang, et al.
Pubblicazione: (2022)

A Convex Framework for Confounding Robust Inference
di: Ishikawa, Kei, et al.
Pubblicazione: (2023)

A Hessian-Aware Stochastic Differential Equation for Modelling SGD
di: Li, Xiang, et al.
Pubblicazione: (2024)

Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning
di: Zhang, Xiaoyu, et al.
Pubblicazione: (2024)

Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections
di: Xu, Xiaomeng, et al.
Pubblicazione: (2025)

Manifold Generalization Provably Proceeds Memorization in Diffusion Models
di: Shen, Zebang, et al.
Pubblicazione: (2026)

GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
di: Xiang, Zhen, et al.
Pubblicazione: (2024)

From Gradient Clipping to Normalization for Heavy Tailed SGD
di: Hübler, Florian, et al.
Pubblicazione: (2024)

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
di: Cayci, Semih, et al.
Pubblicazione: (2021)

ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
di: Zhang, Yilang, et al.
Pubblicazione: (2026)

TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-Tubes
di: Lemmel, Julian, et al.
Pubblicazione: (2025)

When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
di: Li, Xiang, et al.
Pubblicazione: (2025)

CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction
di: Kobayashi, Taisuke
Pubblicazione: (2025)

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
di: Wei, Yudong, et al.
Pubblicazione: (2025)

On the Crucial Role of Initialization for Matrix Factorization
di: Li, Bingcong, et al.
Pubblicazione: (2024)

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
di: Zhang, Liang, et al.
Pubblicazione: (2023)

Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
di: Hu, Yifan, et al.
Pubblicazione: (2020)