Imagen de Portada

PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Yu, Zhang, Wenxiao, Cao, Cong, Lu, Wenxuan, Yuan, Fangfang, Guo, Diandian, Peng, Kun, Sun, Qiang, Zhang, Kaiyan, Liu, Yanbing, Hong, Jin B., Zhou, Bowen, Ma, Zhiyuan
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering
por: Liu, Yu, et al.
Publicado: (2026)

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
por: Liu, Yu, et al.
Publicado: (2025)

Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval
por: Liu, Yu, et al.
Publicado: (2026)

Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering
por: Chen, Mingda, et al.
Publicado: (2023)

End-to-End Beam Retrieval for Multi-Hop Question Answering
por: Zhang, Jiahao, et al.
Publicado: (2023)

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
por: Zhuang, Ziyuan, et al.
Publicado: (2024)

Question Calibration and Multi-Hop Modeling for Temporal Question Answering
por: Xue, Chao, et al.
Publicado: (2024)

Multi-View Incongruity Learning for Multimodal Sarcasm Detection
por: Guo, Diandian, et al.
Publicado: (2024)

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
por: Lu, Yifan, et al.
Publicado: (2024)

Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
por: Long, Xinwei, et al.
Publicado: (2025)

Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
por: Ji, Yuelyu, et al.
Publicado: (2025)

Credible Plan-Driven RAG Method for Multi-Hop Question Answering
por: Zhang, Ningning, et al.
Publicado: (2025)

Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
por: Zhang, Yuxin, et al.
Publicado: (2025)

ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
por: Zhu, Yikai, et al.
Publicado: (2026)

Open Domain Question Answering with Conflicting Contexts
por: Liu, Siyi, et al.
Publicado: (2024)

Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
por: Welz, Simon, et al.
Publicado: (2025)

TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering
por: Li, Zhonghao, et al.
Publicado: (2025)

Can Multimodal Large Language Model Think Analogically?
por: Guo, Diandian, et al.
Publicado: (2024)

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
por: Zhu, Rongzhi, et al.
Publicado: (2025)

M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering
por: Ma, Jiatong, et al.
Publicado: (2026)

BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
por: Zhang, Taolin, et al.
Publicado: (2025)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
por: Shi, Yucheng, et al.
Publicado: (2024)

Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering
por: Gao, Yuan, et al.
Publicado: (2024)

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
por: Shi, Yuling, et al.
Publicado: (2026)

CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
por: Yang, Hao, et al.
Publicado: (2026)

StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
por: Ni, Tengjun, et al.
Publicado: (2025)

PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
por: Nahid, Md Mahadi Hasan, et al.
Publicado: (2025)

REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
por: Zhu, Yijie, et al.
Publicado: (2025)

Knowledge Dependency Estimation for Reliable Question Answering
por: Tong, Chaodong, et al.
Publicado: (2026)

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
por: Thompson, Travis, et al.
Publicado: (2025)

DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering
por: Wang, Xinyi, et al.
Publicado: (2025)

Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
por: Sun, Hongda, et al.
Publicado: (2024)

Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3
por: Huang, Xinyue, et al.
Publicado: (2025)

Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering
por: Ji, Binquan, et al.
Publicado: (2025)

MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries
por: Campi, Riccardo, et al.
Publicado: (2026)

Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis
por: Simon, Dominic, et al.
Publicado: (2025)

A Method for Multi-Hop Question Answering on Persian Knowledge Graph
por: Ghafouri, Arash, et al.
Publicado: (2025)

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
por: Murphy, Alexander, et al.
Publicado: (2025)

DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering
por: Cheng, Rong, et al.
Publicado: (2025)

GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering
por: Sun, Xin, et al.
Publicado: (2026)