Newest papers

Remembering Through Change: Provenance-Preserving Hypergraph Memory for Multimodal Agents

Jielong Tang, Ling-An Zeng, Xujie Yuan, Xiao Dong, Zhiqian Xia, Qingfeng Li, Shixiong Kai, Kaichao Liang, Rong Yao, Jian Yin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29995 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

A memória de longo prazo para os agentes multimodais permanece desafiadora, uma vez que deve preservar evidências visuais finas enquanto rastreia a evolução da entidade através de sessões. As memórias efetivas baseadas em abstração existentes comprimem imagens em texto, muitas vezes descartando detalhes visualmente discriminatórios, enquanto as memórias de conservação de pixels retêm observações brutas, mas lutam para associar de forma confiável várias observações com identidades de entidade persistentes e rastrear seus estados em evolução. Para abordar essas limitações, propomos o MHG-Mem, uma memória hipergráfica multimodal que organiza conjuntamente a identidade da entidade, a evolução do estado e a proveniência para evidências visuais. Especificamente, o MHG-Mem representa menções distintas de entidades

Machine translation (Meta M2M100); the English original follows.

Abstract

Long-term memory for multimodal agents remains challenging, as it must preserve fine-grained visual evidence while tracking entity evolution across sessions. Existing abstraction-based memories compress images into text, often discarding visually discriminative details, whereas pixel-preserving memories retain raw observations but struggle to reliably associate diverse observations with persistent entity identities and track their evolving states. To address these limitations, we propose MHG-Mem, a multimodal hypergraph memory that jointly organizes entity identity, state evolution, and provenance to visual evidence. Specifically, MHG-Mem represents distinct entity mentions and their observed facts as individual nodes, grouping identity-consistent mentions and facts through occurrence hyperedges. It then synthesizes aspect-specific evolution states from these grouped observations and links them to supporting entities, facts, and source evidence through evolutionary and evidential hyperedges. To navigate this structured memory, we introduce hypergraph-based agentic search, which adaptively selects an entry layer, traverses typed hyperedges across memory levels, and inspects source observations when fine-grained verification is required. These designs support both detailed visual verification and reasoning over cross-session state changes. Extensive experiments across three benchmarks demonstrate the effectiveness of MHG-Mem, improving performance by 8.20-9.98% over the strongest baseline.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Discriminative model, Hypergraph, Artificial intelligence, State (computer science), Natural language processing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange