GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning

• URL: http://arxiv.org/abs/2609.14066v1
• Date: Sat, 12 Sep 2026 17:28:45 GMT
• Title: GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning
• Abstract summary: GraMRAG is a graph memory-guided multi-agent RAG framework that integrates a dynamic multimodal memory graph.<n>We introduce a vision-text bridged reasoning paradigm that unifies multi-scale entity cropping with a ReAct-style visual toolchain.<n>We also construct a multimodal memory graph that formalizes agent reasoning as a dynamic directed acyclic graph.
• Score: 3.7070385396772916
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they remain fundamentally limited in reasoning depth and memory structure, suffering from inadequate retrieval and state blindness when answering knowledge-intensive questions. To address these limitations, we propose GraMRAG, a graph memory-guided multi-agent RAG framework that integrates a dynamic multimodal memory graph to enable stable, multi-step multimodal reasoning. We introduce a vision-text bridged reasoning paradigm that unifies multi-scale entity cropping with a ReAct-style visual toolchain, enhancing the long-horizon cross-modal reasoning capability. We further construct a multimodal memory graph that formalizes agent reasoning as a dynamic directed acyclic graph (DAG), explicitly modeling action-observation dependencies to mitigate state blindness and suppress redundant retrieval. Moreover, we propose Topology-Aware Policy Optimization (TAPO) that leverages graph topology for critical path identification and targeted node pruning, enabling fine-grained credit assignment across multi-step reasoning trajectories. Extensive experiments on challenging multimodal benchmarks demonstrate that our approach consistently outperforms existing baselines and achieves state-of-the-art performance on complex long-horizon reasoning tasks.

Related papers

• GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG [4.035350563640088]
  We present GraphLoom, a reliability-calibrated multimodal knowledge-graph RAG framework for compact and faithful evidence routing.<n>Instead of injecting all retrieved evidence into the generator, GraphLoom performs reliability-aware subgraph retrieval.<n>We show consistent gains in answer quality and evidence faithfulness over strong multimodal RAG, graph-retrieval, and open-source vision-language baselines.
  arXiv  Detail & Related papers  (2026-08-15T06:02:23Z)
• Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models [65.4947731385794]
  We present a unified multi-agent visual reasoning framework that evolves from our foundational image-centric model, Insight-V.<n>We introduce two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness.<n>Experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-03-18T15:28:07Z)
• VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph [42.348770377488094]
  VimRAG is a framework tailored for multimodal Retrieval-augmented Reasoning across text, images, and videos.<n>We propose a Graph-Guided Policy Optimization strategy to disentangle step-wise validity from trajectory-level rewards.<n>Experiments demonstrate that VimRAG consistently achieves state-of-the-art performance on diverse multimodal RAG benchmarks.
  arXiv  Detail & Related papers  (2026-02-13T09:05:09Z)
• DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories [52.57197752244638]
  We introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task.<n>Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues.<n>We construct DISBench, a challenging benchmark built on interconnected visual data.
  arXiv  Detail & Related papers  (2026-02-11T12:51:10Z)
• Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling [83.29209853451697]
  Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs)<n>We introduce HGMem, a hypergraph-based memory mechanism that extends the concept of memory into a dynamic, expressive structure for complex reasoning and global understanding.<n>In our approach, memory is represented as a hypergraph whose hyperedges correspond to distinct memory units, enabling the progressive formation of higher-order interactions within memory.
  arXiv  Detail & Related papers  (2025-12-30T03:13:10Z)
• M$^3$Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation [18.091284320771006]
  We propose a novel Multi-Modal Multi-agent hierarchical communication graph PRUNING framework, termed M$3$Prune.<n>Our framework eliminates redundant edges across different modalities, achieving an optimal balance between task performance and token overhead.<n>Our method consistently outperforms both single-agent and robust multi-agent mRAG systems.
  arXiv  Detail & Related papers  (2025-11-25T06:29:13Z)
• Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations [34.15274225730601]
  We propose textbfAgent-ScanKit to unravel the memory and reasoning capabilities of multimodal agents under controlled perturbations.<n>Results show that mechanical memorization often outweighs systematic reasoning.<n>Our findings underscore the necessity of robust reasoning modeling for multimodal agents in real-world scenarios.
  arXiv  Detail & Related papers  (2025-10-01T04:29:39Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.