Image de couverture de livre

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hatgis-Kessell, Stephane, Brunskill, Emma
Format:	Preprint
Publié:	2026
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

Repairing Reward Functions with Feedback to Mitigate Reward Hacking
par: Hatgis-Kessell, Stephane, et autres
Publié: (2025)

Influencing Humans to Conform to Preference Models for RLHF
par: Hatgis-Kessell, Stephane, et autres
Publié: (2025)

Predicting Long Term Sequential Policy Value Using Softer Surrogates
par: Nam, Hyunji, et autres
Publié: (2024)

Experiment Planning with Function Approximation
par: Pacchiano, Aldo, et autres
Publié: (2024)

Partial Policy Gradients for RL in LLMs
par: Mathur, Puneet, et autres
Publié: (2026)

Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
par: Fan, Flint Xiaofeng, et autres
Publié: (2025)

Imbalanced Gradients in RL Post-Training of Multi-Task LLMs
par: Wu, Runzhe, et autres
Publié: (2025)

Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
par: Huang, Luke J., et autres
Publié: (2026)

Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling
par: Li, Derek, et autres
Publié: (2025)

Soft Policy Optimization: Online Off-Policy RL for Sequence Models
par: Cohen, Taco, et autres
Publié: (2025)

Sequential Policy Gradient for Adaptive Hyperparameter Optimization
par: Li, Zheng, et autres
Publié: (2025)

Adaptive Interventions with User-Defined Goals for Health Behavior Change
par: Mandyam, Aishwarya, et autres
Publié: (2023)

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
par: Fakoor, Rasool, et autres
Publié: (2026)

When Stability meets Sufficiency: Informative Explanations that do not Overwhelm
par: Luss, Ronny, et autres
Publié: (2021)

Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
par: Abdulsamad, Hany, et autres
Publié: (2025)

When Maximum Entropy Misleads Policy Optimization
par: Zhang, Ruipeng, et autres
Publié: (2025)

ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
par: He, Zelin, et autres
Publié: (2026)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
par: Zeng, Yifan, et autres
Publié: (2026)

Anytime-Valid Answer Sufficiency Certificates for LLM Generation via Sequential Information Lift
par: Akter, Sanjeda, et autres
Publié: (2025)

When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
par: Zhang, Yizhou
Publié: (2025)

Autoregressive Policy Optimization for Constrained Allocation Tasks
par: Winkel, David, et autres
Publié: (2024)

Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
par: Mark, Max Sobol, et autres
Publié: (2024)

Language Model Embeddings Can Be Sufficient for Bayesian Optimization
par: Nguyen, Tung, et autres
Publié: (2024)

Calibration-Aware Policy Optimization for Reasoning LLMs
par: Wang, Ziqi, et autres
Publié: (2026)

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
par: Zheng, Haizhong, et autres
Publié: (2025)

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
par: Liu, Zongkai, et autres
Publié: (2024)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
par: Zhao, Hao, et autres
Publié: (2024)

RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs
par: Samineni, Soumya Rani, et autres
Publié: (2025)

One-Way Policy Optimization for Self-Evolving LLMs
par: Yang, Shuo, et autres
Publié: (2026)

Bootstrapping LLMs via Preference-Based Policy Optimization
par: Jia, Chen
Publié: (2025)

ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding
par: Zhoubian, Sining, et autres
Publié: (2025)

Scalable Policy-Based RL Algorithms for POMDPs
par: Anjarlekar, Ameya, et autres
Publié: (2025)

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
par: Zhang, Yiqi, et autres
Publié: (2026)

A Systematic Investigation of The RL-Jailbreaker in LLMs
par: Mohammedalamen, Montaser, et autres
Publié: (2026)

Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
par: He, Shuo, et autres
Publié: (2026)

SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments
par: Ishida, Shu, et autres
Publié: (2024)

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
par: Liu, Shih-Yang, et autres
Publié: (2026)

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
par: Lee, Haanvid, et autres
Publié: (2024)

Representation Learning for Sequential Volumetric Design Tasks
par: Alam, Md Ferdous, et autres
Publié: (2023)

Policy Learning for Off-Dynamics RL with Deficient Support
par: Van, Linh Le Pham, et autres
Publié: (2024)