pith. sign in

arxiv: 2507.09477 · v2 · pith:CUIB37BZnew · submitted 2025-07-13 · 💻 cs.CL · cs.AI

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

classification 💻 cs.CL cs.AI
keywords reasoningllmsrag-reasoningagenticinferenceknowledgesurveysystems
0
0 comments X
read the original abstract

Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). Finally, we spotlight emerging Synergized RAG-Reasoning frameworks, where (agentic) LLMs iteratively interleave search and reasoning to achieve state-of-the-art performance across knowledge-intensive benchmarks. We categorize methods, datasets, and open challenges, and outline research avenues toward deeper RAG-Reasoning systems that are more effective, multimodally-adaptive, trustworthy, and human-centric. The collection is available at https://github.com/DavidZWZ/Awesome-RAG-Reasoning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

    cs.DC 2026-05 conditional novelty 7.0

    KVServe delivers up to 9.13x job completion time speedup and 32.8x time-to-first-token reduction by making KV cache compression service-aware and adaptive in disaggregated LLM serving.

  2. Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

    cs.CL 2026-06 unverdicted novelty 6.0

    PEEU enables a 7B MLLM to reach 30.6% accuracy on GUI task planning by autonomous exploration and hindsight experience synthesis, outperforming a 32B model through stronger high-level OOD generalization.

  3. GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

    cs.AI 2026-04 unverdicted novelty 6.0

    GAM decouples event-level memory encoding from topic-level consolidation in LLM agents using hierarchical graphs to reduce interference and improve long-term coherence and retrieval.

  4. RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills

    cs.CL 2026-06 unverdicted novelty 5.0

    RubricsTree is a scalable, evolving rubric-based evaluation system with adaptive routing that improves physician alignment for health AI responses and enables performance gains when used as feedback or rewards.

  5. RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching

    cs.DB 2026-06 unverdicted novelty 5.0

    RACT is a retrieval-augmented self-supervised method that improves multi-table schema matching precision and completeness by up to 70% by probabilistically retrieving relevant tables to limit column candidate search space.

  6. Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings

    cs.IR 2026-05 unverdicted novelty 5.0

    Proposes LLM-driven logical retrieval in agentic RAG with inverted-index backend, matching hybrid baselines at lower cost and with reduced hallucinations.

  7. Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval

    cs.CV 2026-01 unverdicted novelty 4.0

    Large-scale profiling of recent AI literature shows growth in safety, multimodal reasoning, and agent studies alongside stabilization in neural machine translation and graph methods.

  8. Toward Agentic RAG for Ukrainian

    cs.AI 2026-04 unverdicted novelty 3.0

    Agentic RAG for Ukrainian improves answer accuracy via retries but is still limited by document and page retrieval quality.