Cover Image

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xuancheng, Li, Haitao, Zhou, Yujia, Liu, Yiqun, Ai, Qingyao
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
by: Li, Xuancheng, et al.
Published: (2026)

MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop
by: Li, Xuancheng, et al.
Published: (2026)

Beyond Scalar Reward Model: Learning Generative Judge from Preference Data
by: Ye, Ziyi, et al.
Published: (2024)

Option-ID Based Elimination For Multiple Choice Questions
by: Zhu, Zhenhao, et al.
Published: (2025)

Beyond Error-Based Optimization: Experience-Driven Symbolic Regression with Goal-Conditioned Reinforcement Learning
by: Sun, Jianwen, et al.
Published: (2026)

MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
by: Ai, Qingyao, et al.
Published: (2025)

What Scales in Cross-Entropy Scaling Law?
by: Yan, Junxi, et al.
Published: (2025)

Relative-Based Scaling Law for Neural Language Models
by: Yue, Baoqing, et al.
Published: (2025)

Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
by: Zhang, Xinnan, et al.
Published: (2025)

Beyond Exposure: Optimizing Ranking Fairness with Non-linear Time-Income Functions
by: Li, Xuancheng, et al.
Published: (2026)

StructSynth: Leveraging LLMs for Structure-Aware Tabular Data Synthesis in Low-Data Regimes
by: Liu, Siyi, et al.
Published: (2025)

Re:Frame -- Retrieving Experience From Associative Memory
by: Zelezetsky, Daniil, et al.
Published: (2025)

Trained Persistent Memory for Frozen Decoder-Only LLMs
by: Jeong, Hong
Published: (2026)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
by: Wang, Changyue, et al.
Published: (2025)

Evaluation Ethics of LLMs in Legal Domain
by: Zhang, Ruizhe, et al.
Published: (2024)

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
by: Zhang, Zeyu, et al.
Published: (2026)

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
by: Zhao, Kaiyan, et al.
Published: (2024)

CIER: A Novel Experience Replay Approach with Causal Inference in Deep Reinforcement Learning
by: Wang, Jingwen, et al.
Published: (2024)

Scalable and reliable deep transfer learning for intelligent fault detection via multi-scale neural processes embedded with knowledge
by: Li, Zhongzhi, et al.
Published: (2024)

Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs
by: Meng, Fei
Published: (2026)

ExGRPO: Learning to Reason from Experience
by: Zhan, Runzhe, et al.
Published: (2025)

Beyond Relevance: Utility-Centric Retrieval in the LLM Era
by: Zhang, Hengran, et al.
Published: (2026)

Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
by: Wu, Lirong, et al.
Published: (2024)

Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs
by: Xu, Minghui, et al.
Published: (2026)

On the Identifiability of Nonlinear ICA: Sparsity and Beyond
by: Zheng, Yujia, et al.
Published: (2022)

Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods
by: Jeong, Hong
Published: (2026)

Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization
by: Carstensen, Timur, et al.
Published: (2025)

Environment Scaling for Interactive Agentic Experience Collection: A Survey
by: Huang, Yuchen, et al.
Published: (2025)

Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences
by: Hiraoka, Takuya, et al.
Published: (2024)

FLEX: Continuous Agent Evolution via Forward Learning from Experience
by: Cai, Zhicheng, et al.
Published: (2025)

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
by: Huang, Shiting, et al.
Published: (2026)

Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study
by: Niu, Zechun, et al.
Published: (2024)

MemER: Scaling Up Memory for Robot Control via Experience Retrieval
by: Sridhar, Ajay, et al.
Published: (2025)

SplitFrozen: Split Learning with Device-side Model Frozen for Fine-Tuning LLM on Heterogeneous Resource-Constrained Devices
by: Ma, Jian, et al.
Published: (2025)

Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval
by: Su, Weihang, et al.
Published: (2023)

Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal
by: Hu, Jifeng, et al.
Published: (2024)

IDER: IDempotent Experience Replay for Reliable Continual Learning
by: Liu, Zhanwang, et al.
Published: (2026)

Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning
by: Li, Keyu, et al.
Published: (2021)

Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation
by: Wang, Xiaoda, et al.
Published: (2025)

Generalized Back-Stepping Experience Replay in Sparse-Reward Environments
by: Lyu, Guwen, et al.
Published: (2024)