Metraipolis › archive › dc_a67cdd8eaa29
GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning — arXiv:2609.14066
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14066
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:50:52.328Z
- SHA-256 of the archived text
764a607999cf09e78b4e3f6bf64c28a3a6a77beafccbb270b662e92a0d978738- Stable URL of this page
https://metraipolis.com/documento/dc_a67cdd8eaa29
How to cite
GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning — arXiv:2609.14066 — arXiv (en), https://arxiv.org/abs/2609.14066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a67cdd8eaa29 (Metraipolis archive dc_a67cdd8eaa29, sha256 764a607999cf09e78b4e3f6bf64c28a3a6a77beafccbb270b662e92a0d978738)
BibTeX
@misc{dca67cdd8eaa29,
title = {GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning — arXiv:2609.14066},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14066},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a67cdd8eaa29; sha256 764a607999cf09e78b4e3f6bf64c28a3a6a77beafccbb270b662e92a0d978738},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.14066 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:29:03.612Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).