Image de couverture de livre

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wei, Jiaqi, Zhou, Hao, Zhang, Xiang, Zhang, Di, Qiu, Zijie, Wei, Wei, Li, Jinzhe, Ouyang, Wanli, Sun, Siqi
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
par: Wei, Jiaqi, et autres
Publié: (2026)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
par: Zhang, Xiang, et autres
Publié: (2025)

Enhancing Retrieval Systems with Inference-Time Logical Reasoning
par: Faltings, Felix, et autres
Publié: (2025)

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
par: Xi, Zhiheng, et autres
Publié: (2024)

Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
par: Li, Bo, et autres
Publié: (2025)

Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
par: Wei, Jiaqi, et autres
Publié: (2025)

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
par: Chen, Zihong, et autres
Publié: (2025)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
par: Sun, Renliang, et autres
Publié: (2025)

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

LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
par: Chen, Zerui, et autres
Publié: (2026)

ROGRAG: A Robustly Optimized GraphRAG Framework
par: Wang, Zhefan, et autres
Publié: (2025)

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
par: Wang, Yu, et autres
Publié: (2025)

Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
par: Wu, Di, et autres
Publié: (2025)

LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
par: Li, Shaojun, et autres
Publié: (2024)

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
par: Li, Yansi, et autres
Publié: (2025)

Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis
par: Long, Zhuohan, et autres
Publié: (2026)

GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation
par: Xiao, Yilin, et autres
Publié: (2025)

Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models
par: Li, Jinzhe, et autres
Publié: (2025)

DocReLM: Mastering Document Retrieval with Language Model
par: Wei, Gengchen, et autres
Publié: (2024)

REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation
par: Jiang, Wentao, et autres
Publié: (2025)

A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
par: Yuan, Ye, et autres
Publié: (2024)

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
par: Jiang, Jinhao, et autres
Publié: (2024)

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
par: Wei, Zhepei, et autres
Publié: (2024)

SaRO: Enhancing LLM Safety through Reasoning-based Alignment
par: Mou, Yutao, et autres
Publié: (2025)

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
par: Zhang, Xiaoying, et autres
Publié: (2025)

CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG
par: Wang, Ziting, et autres
Publié: (2024)

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
par: Wang, Zilong, et autres
Publié: (2024)

Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
par: Qi, Zehan, et autres
Publié: (2024)

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
par: She, Shuaijie, et autres
Publié: (2024)

Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG
par: Zhao, Zijie, et autres
Publié: (2026)

Exploring Sound Change Over Time: A Review of Computational and Human Perception
par: He, Siqi, et autres
Publié: (2024)

DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning
par: Sun, Qingyun, et autres
Publié: (2025)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
par: Zhang, Xiang, et autres
Publié: (2025)

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
par: Wang, Juyuan, et autres
Publié: (2025)

Optimizing Retrieval for RAG via Reinforcement Learning
par: Zhou, Jiawei, et autres
Publié: (2025)

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
par: Liu, Runze, et autres
Publié: (2025)

CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
par: Yang, Hao, et autres
Publié: (2026)

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
par: Zhou, Jiawei, et autres
Publié: (2025)

Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback
par: Afzal, Osama Mohammed, et autres
Publié: (2025)

You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
par: Chen, Shengyuan, et autres
Publié: (2025)