Image de couverture de livre

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Ziliang, An, Kang, Zheng, Xuhui, Qian, Faqiang, Zhang, Weikun, Ouyang, Cijun, Cai, Jialu, Wang, Yuhang, Wu, Yichao
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence Information Retrieval
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization
par: Wang, Ziliang, et autres
Publié: (2025)

MMRPT: MultiModal Reinforcement Pre-Training via Masked Vision-Dependent Reasoning
par: Zheng, Xuhui, et autres
Publié: (2025)

ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation
par: Wang, Zhao, et autres
Publié: (2026)

DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation
par: Zeng, Xingyuan, et autres
Publié: (2026)

MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
par: Zhang, Sheng, et autres
Publié: (2026)

RAGR: Review-Augmented Generative Recommendation
par: Zhang, Yingyi, et autres
Publié: (2026)

Retrieval Augmented Conversational Recommendation with Reinforcement Learning
par: Yue, Zhenrui, et autres
Publié: (2026)

M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions
par: Wang, Zheng, et autres
Publié: (2024)

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
par: Chen, Yiqun, et autres
Publié: (2025)

Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning
par: Li, Jinzheng, et autres
Publié: (2025)

Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
par: Liu, Yuhang, et autres
Publié: (2024)

Reinforced Preference Optimization for Reasoning-Augmented Recommendations
par: Gao, Jingtong, et autres
Publié: (2026)

DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning
par: Jiang, Pengcheng, et autres
Publié: (2025)

Search Arena: Analyzing Search-Augmented LLMs
par: Miroyan, Mihran, et autres
Publié: (2025)

To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
par: Zhang, Wenlin, et autres
Publié: (2026)

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
par: Jin, Bowen, et autres
Publié: (2025)

Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance
par: Xu, Tingqiao, et autres
Publié: (2025)

LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models
par: Yan, Yang, et autres
Publié: (2024)

An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs
par: Ma, Linyue, et autres
Publié: (2025)

Decoupled Residual Quantization for Robust Semantic IDs in Recommendation
par: Wang, Xuesi, et autres
Publié: (2026)

Improve Temporal Awareness of LLMs for Sequential Recommendation
par: Chu, Zhendong, et autres
Publié: (2024)

LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce
par: Zhang, Yipeng, et autres
Publié: (2025)

A Multi-Task Embedder For Retrieval Augmented LLMs
par: Zhang, Peitian, et autres
Publié: (2023)

Improving Search Suggestions for Alphanumeric Queries
par: Agrawal, Samarth, et autres
Publié: (2026)

OASIS: Order-Augmented Strategy for Improved Code Search
par: Gao, Zuchen, et autres
Publié: (2025)

TongSearch-QR: Reinforced Query Reasoning for Retrieval
par: Qin, Xubo, et autres
Publié: (2025)

ScholarSearch: Benchmarking Scholar Searching Ability of LLMs
par: Zhou, Junting, et autres
Publié: (2025)

Improving LLM Interpretability and Performance via Guided Embedding Refinement for Sequential Recommendation
par: Jia, Nanshan, et autres
Publié: (2025)

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
par: Cheng, Yiruo, et autres
Publié: (2024)

Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback
par: Wang, Zheng, et autres
Publié: (2024)

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
par: Zhang, Wenlin, et autres
Publié: (2025)

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
par: Dai, Yuqin, et autres
Publié: (2025)

Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search
par: Liu, Xingxian, et autres
Publié: (2025)

Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace Tuning
par: Zhao, Jujia, et autres
Publié: (2026)

Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
par: Ju, Jia-Huei, et autres
Publié: (2026)

Zero-Indexing Internet Search Augmented Generation for Large Language Models
par: He, Guangxin, et autres
Publié: (2024)

A Survey of Conversational Search
par: Mo, Fengran, et autres
Publié: (2024)

RLTP: Reinforcement Learning to Pace for Delayed Impression Modeling in Preloaded Ads
par: Wei, Penghui, et autres
Publié: (2023)

Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
par: Chen, Haonan, et autres
Publié: (2024)

Enhancing LLM-based Recommendation with Preference Hint Discovery from Knowledge Graph
par: Zhang, Yuting, et autres
Publié: (2026)