Imagen de Portada

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Weitao, Xiang, Boran, Wang, Xiaolong, Gou, Zhinan, Ma, Weizhi, Liu, Yang
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Citation-Enhanced Generation for LLM-based Chatbots
por: Li, Weitao, et al.
Publicado: (2024)

Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning
por: Ren, Jingyi, et al.
Publicado: (2025)

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
por: Li, Yangning, et al.
Publicado: (2025)

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
por: Li, Yuan, et al.
Publicado: (2025)

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
por: Wang, Yunxiao, et al.
Publicado: (2025)

Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning
por: Huo, Nan, et al.
Publicado: (2025)

CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
por: Tan, Zhehao, et al.
Publicado: (2026)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
por: Wang, Haozhe, et al.
Publicado: (2025)

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
por: Wei, Jiaqi, et al.
Publicado: (2025)

GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
por: Luo, Jinchang, et al.
Publicado: (2025)

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
por: Zhang, Tunyu, et al.
Publicado: (2025)

Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment
por: Liu, Junming, et al.
Publicado: (2026)

Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
por: Lin, Junhong, et al.
Publicado: (2025)

DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
por: Ren, Z. Z., et al.
Publicado: (2025)

Zero, Finite, and Infinite Belief History of Theory of Mind Reasoning in Large Language Models
por: Tang, Weizhi, et al.
Publicado: (2024)

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
por: Chen, Yang, et al.
Publicado: (2025)

ToM-LM: Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models
por: Tang, Weizhi, et al.
Publicado: (2024)

Reinforcement Learning for Optimizing RAG for Domain Chatbots
por: Kulkarni, Mandar, et al.
Publicado: (2024)

Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables
por: Gong, Haisong, et al.
Publicado: (2024)

Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning
por: Zhang, Xiaotian, et al.
Publicado: (2025)

StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
por: Wan, Luanbo, et al.
Publicado: (2025)

CARE-RAG - Clinical Assessment and Reasoning in RAG
por: Potluri, Deepthi, et al.
Publicado: (2025)

DROJ: A Prompt-Driven Attack against Large Language Models
por: Hu, Leyang, et al.
Publicado: (2024)

RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning
por: Li, Gang, et al.
Publicado: (2025)

RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
por: Guo, Yucan, et al.
Publicado: (2025)

LTLBench: Towards Benchmarks for Evaluating Temporal Reasoning in Large Language Models
por: Tang, Weizhi, et al.
Publicado: (2024)

How Much Can RAG Help the Reasoning of LLM?
por: Liu, Jingyu, et al.
Publicado: (2024)

STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing
por: Stoisser, Josefa Lia, et al.
Publicado: (2025)

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
por: Wang, Yu, et al.
Publicado: (2025)

SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
por: Acikgoz, Emre Can, et al.
Publicado: (2025)

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
por: Jiang, Jinhao, et al.
Publicado: (2024)

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models
por: Chen, Guanxu, et al.
Publicado: (2025)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
por: Wen, Xumeng, et al.
Publicado: (2025)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
por: Xu, Hongling, et al.
Publicado: (2025)

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
por: Wu, Jiayi, et al.
Publicado: (2024)

S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering
por: Fu, Rong, et al.
Publicado: (2026)

GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization
por: Ye, Yangfan, et al.
Publicado: (2024)

No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
por: Rajgaria, Abhishek, et al.
Publicado: (2025)

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning
por: Kachuee, Mohammad, et al.
Publicado: (2025)

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
por: Du, Dong, et al.
Publicado: (2025)