D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding

• URL: http://arxiv.org/abs/2608.16417v1
• Date: Mon, 17 Aug 2026 11:15:27 GMT
• Title: D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding
• Abstract summary: D2-ScaleAgent is an agentic framework that introduces a dual-dimensional scaling paradigm for retrieval and reasoning.<n>D2-ScaleAgent is effective on long and visually rich document benchmarks like MMLongBench-Doc, LongDocURL, etc.
• Score: 28.415704604103112
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively advancing toward multi-agent systems: they first retrieve relevant pages based on a query, and then iteratively understand information within those pages. However, these methods typically rely on fixed workflows and lack the ability to dynamically scale computation at test time, often leading to insufficient evidence. To address this, we propose D2-ScaleAgent, an agentic framework that introduces a dual-dimensional scaling paradigm for retrieval and reasoning. The core of D2-ScaleAgent is a Verifier agent-driven dynamic routing loop based on the intrinsic difficulty of the query, centered around a continuously updated evidence bank that serves as the agent's dynamic working memory: when retrieval needs to be expanded, the agent routes outward (retrieval scaling), decomposing the query into attributes and performing parallel page retrieval, followed by adaptive pruning to ensure comprehensive evidence coverage. When fine-grained reasoning is required, the agent routes inward (reasoning scaling), dynamically selecting sub-agents with varying granularity and count to extract evidence from pages. Finally, D2-ScaleAgent achieves logical closure over the evidence chain. Extensive experiments demonstrate that D2-ScaleAgent is effective on long and visually rich document benchmarks like MMLongBench-Doc, LongDocURL, etc.

Related papers

• SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration [77.28003194268977]
  SearchOS is a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state.<n>Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents.<n>SearchOS leads all metrics among the evaluated single- and multi-agent baselines.
  arXiv  Detail & Related papers  (2026-07-16T17:51:23Z)
• WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search [104.75798763084424]
  Large language model (LLM)-based web search agents are transforming information seeking into complex, deep-and-wide search and research-oriented tasks.<n>We propose WebSwarm, a progressive progressive delegation framework that jointly constructs task decomposition and expansion.<n>We show that WebSwarm consistently outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks.
  arXiv  Detail & Related papers  (2026-07-09T16:28:49Z)
• Hierarchical Evidence-Driven Reasoning for Long Document Understanding [95.51688464037096]
  We introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding.<n>Our framework significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
  arXiv  Detail & Related papers  (2026-07-06T03:08:28Z)
• Hybrid Retriever Evolution for Multimodal Document Reasoning Agents [7.9215284090523355]
  We introduce a failure-driven evolution framework in which a meta-agent autonomously discovers how a tool-using task agent should coordinate diverse retrievers.<n>On MMLongBench-Doc and DocBench, the evolved agent achieves gains of up to +19.6 points over the unevolved baseline.
  arXiv  Detail & Related papers  (2026-06-28T23:36:34Z)
• Reason Before You Retrieve: Agentic Planning for Multi-modal RAG [37.890744636035144]
  We propose MM-R2, a multimodal agentic retrieval framework that reasons before retrieval by explicitly modeling both what to retrieve and where to search.<n> MM-R2 first constructs an intent-grounded retrieval state from the image-question pair, capturing the information need, grounded referent, and retrieval constraints.<n>It then performs retrieval over a structured KnowledgeMap, where the agent selects relevant retrieval units before issuing grounded queries within them.<n>Experiments on Infoseek and Encyclopedic VQA datasets show that MM-R2 substantially outperforms strong baselines on answer accuracy while also yielding more interpretable and verifiable retrieval trajectories.
  arXiv  Detail & Related papers  (2026-06-24T02:40:49Z)
• VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents [0.0]
  We present VLD-RAG, an agentic multimodal RAG framework for multi-page evidence retrieval and cross-page reasoning over long documents.<n>VLD-RAG builds a page-preserving multimodal index that stores parsed text, page-level metadata, and dense visual representations.<n>A verifier-guided agent workflow coordinates a Retrieval Agent, Answer Agent, and Validation Agent to broaden evidence coverage, detect missing citations, and refine retrieval requests.
  arXiv  Detail & Related papers  (2026-05-21T13:33:38Z)
• Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction [38.55682016152131]
  textbfWeb2BigTable is a multi-agent framework for web-to-table search.<n>Web2BigTable sets a new state of the art on WideSearch, reaching an Avg@4 Success Rate of textbf38.50 ($7.5times$ the second best at 5.10), Row F1 of textbf63.53 (+25.03 over the second best) and Item F1 of textbf80.12 (+14.42 over the second best)<n>It also generalises to depth-oriented search on XBench
  arXiv  Detail & Related papers  (2026-04-29T21:43:16Z)
• Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework [82.66443886385125]
  Paper Circle is a discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature.<n>The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-agent scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes such as concepts, methods, and figures.
  arXiv  Detail & Related papers  (2026-04-07T17:59:58Z)
• A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces [34.59674580962045]
  We introduce A-RAG, an Agentic RAG framework that exposes hierarchical retrieval interfaces directly to the model.<n>A-RAG provides three retrieval tools: keyword search, semantic search, and chunk read, enabling the agent to adaptively search and retrieve information across multiple granularities.<n> Experiments on multiple open-domain QA benchmarks show that A-RAG consistently outperforms existing approaches with comparable or lower retrieved tokens.
  arXiv  Detail & Related papers  (2026-02-03T12:07:21Z)
• T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search [51.91311158085973]
  multimodal misinformation often arises from mixed forgery sources, requiring dynamic reasoning and adaptive verification.<n>We propose T2Agent, a novel misinformation detection agent that incorporates a toolkit with Monte Carlo Tree Search.<n>Extensive experiments show that T2Agent consistently outperforms existing baselines on challenging mixed-source multimodal misinformation benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T09:50:55Z)
• Retrieval-Augmented Reinforcement Learning [63.32076191982944]
  We train a network to map a dataset of past experiences to optimal behavior. The retrieval process is trained to retrieve information from the dataset that may be useful in the current context. We show that retrieval-augmented R2D2 learns significantly faster than the baseline R2D2 agent and achieves higher scores.
  arXiv  Detail & Related papers  (2022-02-17T02:44:05Z)

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.