Image de couverture de livre

Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nourzad, Narjes, Joe-Wong, Carlee
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

MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
par: Nourzad, Narjes, et autres
Publié: (2026)

DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration
par: Nourzad, Narjes, et autres
Publié: (2025)

Smart Routing with Precise Link Estimation: DSEE-Based Anypath Routing for Reliable Wireless Networking
par: Nourzad, Narjes, et autres
Publié: (2024)

Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
par: Zhang, Zuyuan, et autres
Publié: (2026)

An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems
par: Yang, Hanqing, et autres
Publié: (2024)

COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
par: Yang, Hanqing, et autres
Publié: (2026)

Neural Combinatorial Clustered Bandits for Recommendation Systems
par: Atalar, Baran, et autres
Publié: (2024)

Federated Learning with Flexible Architectures
par: Park, Jong-Ik, et autres
Publié: (2024)

Advantage-Guided Diffusion for Model-Based Reinforcement Learning
par: Foffano, Daniele, et autres
Publié: (2026)

FedTLU: Federated Learning with Targeted Layer Updates
par: Park, Jong-Ik, et autres
Publié: (2024)

AURA: Adaptive Unified Reasoning and Automation with LLM-Guided MARL for NextG Cellular Networks
par: Nourzad, Narjes, et autres
Publié: (2025)

Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
par: Kim, Taejin, et autres
Publié: (2023)

The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
par: Chen, Jingdi, et autres
Publié: (2026)

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
par: Le, Thanh-Long V., et autres
Publié: (2025)

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
par: Zhang, Xuechen, et autres
Publié: (2024)

CoRAST: Towards Foundation Model-Powered Correlated Data Analysis in Resource-Constrained CPS and IoT
par: Hu, Yi, et autres
Publié: (2024)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
par: Liu, Tenglong, et autres
Publié: (2024)

QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling
par: Guda, Blessed, et autres
Publié: (2024)

Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
par: Ustaomeroglu, Muhammed, et autres
Publié: (2025)

Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
par: Liu, Xutong, et autres
Publié: (2022)

From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge
par: Wu, Xiefeng
Publié: (2024)

Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
par: Kunde, Vishnu Teja, et autres
Publié: (2026)

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
par: Liu, Weijie, et autres
Publié: (2023)

Fair Concurrent Training of Multiple Models in Federated Learning
par: Siew, Marie, et autres
Publié: (2024)

RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
par: Chen, Jingdi, et autres
Publié: (2024)

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
par: Askin, Baris, et autres
Publié: (2026)

Guiding Exploration in Reinforcement Learning Through LLM-Augmented Observations
par: Jain, Vaibhav, et autres
Publié: (2025)

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
par: Huang, Shiting, et autres
Publié: (2026)

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
par: Liang, Zhenwen, et autres
Publié: (2025)

ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning
par: Ren, Qingnan, et autres
Publié: (2026)

An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space
par: Lin, Hai, et autres
Publié: (2024)

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
par: Fei, Wu, et autres
Publié: (2025)

Quantum Advantage Actor-Critic for Reinforcement Learning
par: Kölle, Michael, et autres
Publié: (2024)

DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
par: Wang, Yujie, et autres
Publié: (2026)

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

On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning
par: Canonaco, Giuseppe, et autres
Publié: (2024)

LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation
par: Tan, Heng, et autres
Publié: (2025)

Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning
par: Fan, Shanwei, et autres
Publié: (2025)

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
par: Liu, Weijie, et autres
Publié: (2025)

Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs
par: Chen, Xinzhu, et autres
Publié: (2025)