DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

• URL: http://arxiv.org/abs/2608.07067v1
• Date: Fri, 07 Aug 2026 10:16:56 GMT
• Title: DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding
• Abstract summary: Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages.<n>We propose DocMemo, a memory-guided framework that formulates long-document reasoning as dynamic evidence exploration.<n> Experiments on 3 benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured memory and dynamic page belief updating.
• Score: 6.3805171496158195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-$k$ page set at the outset and struggle to recover from early retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation mechanism of cross-round states, making it difficult to track the dynamic changes in page relevance. To address these limitations, we propose DocMemo, a memory-guided framework that formulates long-document reasoning as dynamic evidence exploration. DocMemo maintains a tri-level retrieval state consisting of Document Schema Memory, Page Belief Memory, and Question Episodic Memory, which respectively capture structural priors, dynamic relevance estimation, and query-specific reasoning trajectories. During reasoning, DocMemo continuously refines cross-round page selection through Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access, while supplementing page-level evidence with fine-grained visual regions. Experiments on 3 benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured memory and dynamic page belief updating. Code is available at https://github.com/Harrygof/DocMemo.

Related papers

• Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding [64.34948094316685]
  We introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize.<n>LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.
  arXiv  Detail & Related papers  (2026-09-03T17:28:14Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering [11.17007249581283]
  Long-document question answering requires large language models to reason over evidence scattered across lengthy documents.<n>Existing structured RAG methods face three limitations: costly query-agnostic knowledge organization, insufficient use of original document structure, and no reuse of historical reasoning experience.<n>We propose DocTrace, a multi-agent RAG framework for long-document QA that supports query-triggered knowledge organization, document-structure-aware and experience-guided reasoning.
  arXiv  Detail & Related papers  (2026-06-09T14:29:06Z)
• Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory [19.802226925602927]
  Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions.<n>We propose Infini Memory, a maintainable text-based persistent memory architecture that treats agent memory as topic-structured documents.
  arXiv  Detail & Related papers  (2026-06-09T10:31:51Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA [23.25080415779712]
  We propose a Memory-Aware Refinement Agent framework that decouples long-document QA into three specialized agents.<n>Across iterations, the agents rely on a dynamically updated structured memory rather than a full accumulated interaction history.<n>Experiments on MMLongBench-Doc and DocBench show that MARDoc achieves strong results, outperforming same-backbone baselines.
  arXiv  Detail & Related papers  (2026-06-04T06:23:01Z)
• HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning [17.783618926697066]
  Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and interaction histories.<n>We propose HMARS, a hierarchical multi-agent memory system that treats long contexts as managed memory rather than a flat retrieval corpus.
  arXiv  Detail & Related papers  (2026-06-03T07:15:11Z)
• MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory [80.97855900579512]
  Existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning.<n>We introduce MemEye, a framework that evaluates memory capabilities from two dimensions.<n>Under this framework, we construct a new benchmark across 8 life-scenario tasks.
  arXiv  Detail & Related papers  (2026-05-14T17:37:52Z)
• Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA [71.42483000929614]
  Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents.<n>We propose Doc-$V*$, an textbfOCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
  arXiv  Detail & Related papers  (2026-04-15T11:12:27Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• DAPR: A Benchmark on Document-Aware Passage Retrieval [57.45793782107218]
  We propose and name this task emphDocument-Aware Passage Retrieval (DAPR) While analyzing the errors of the State-of-The-Art (SoTA) passage retrievers, we find the major errors (53.5%) are due to missing document context. Our created benchmark enables future research on developing and comparing retrieval systems for the new task.
  arXiv  Detail & Related papers  (2023-05-23T10:39:57Z)
• Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification [21.04611844009438]
  We propose a novel retrieve-and-rerank method for multi-hop retrieval. It consists of a retriever that jointly scores documents in the knowledge source and sentences from previously retrieved documents. It is guided by a proof system that dynamically terminates the retrieval process if the evidence is deemed sufficient.
  arXiv  Detail & Related papers  (2022-12-10T11:32:38Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

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.