TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

• URL: http://arxiv.org/abs/2606.02320v1
• Date: Mon, 01 Jun 2026 14:35:14 GMT
• Title: TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
• Abstract summary: TVIR (Text--Visual Interleaved Report Generation) is a benchmark of 100 expert-curated multimodal deep research tasks.<n>TVIR-Agent is a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines and retrieving images.<n>We develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment.
• Score: 63.89818340842003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements are factually reliable and well aligned with the surrounding analysis. To address this gap, we introduce TVIR (Text--Visual Interleaved Report Generation), which includes TVIR-Bench, a benchmark of 100 expert-curated multimodal deep research tasks that require visual elements to serve specific analytical sub-goals, and TVIR-Agent, a hierarchical multi-agent framework that serves as a strong baseline for constructing outlines, retrieving images, generating charts with traceable sources, and composing reports through context-aware sequential writing. We further develop a dual-path evaluation framework that combines Textual Assessment and Visual Assessment. Experiments across nine deep research systems show that TVIR-Agent achieves strong overall performance, underscoring the importance of explicit multimodal design and evaluation for evidence-driven report generation.

Related papers

• Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation [70.92039951832591]
  We propose textscPtah, a multi-agent harness for interleaved report generation.<n>textscPtah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages.<n>A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow.
  arXiv  Detail & Related papers  (2026-05-28T12:40:34Z)
• ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence [1.6789785654745923]
  We present ViDR, a framework that grounds long-form reports in source figures.<n>ViDR treats source figures as retrievable, interpretable, routable, and verifiable evidence objects.<n>We also introduce MMR Bench+, a benchmark for evaluating visual evidence use in deep research reports.
  arXiv  Detail & Related papers  (2026-05-13T05:39:38Z)
• Towards Knowledgeable Deep Research: Framework and Benchmark [105.87257445617922]
  This paper introduces Knowledgeable Deep Research (KDR), which requires DR agents to generate reports with both structured and unstructured knowledge.<n>We propose the Hybrid Knowledge Analysis framework (HKA), a multi-agent architecture that integrates texts, figures, and tables into coherent multimodal reports.<n> Experimental results demonstrate that HKA consistently outperforms most existing DR agents on general-purpose and knowledge-centric metrics.
  arXiv  Detail & Related papers  (2026-04-09T02:06:27Z)
• 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)
• FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents [53.03492387564392]
  We introduce FS-Researcher, a file-system-based framework that scales deep research beyond the context window via a persistent workspace.<n>A Context Builder agent browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length.<n>A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts.
  arXiv  Detail & Related papers  (2026-02-02T03:00:19Z)
• MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents [37.98503734345155]
  We introduce MMDeepResearch-Bench (MMDR-Bench), a benchmark of 140 expert-crafted tasks across 21 domains.<n>Compared to prior setups, MMDR-Bench emphasizes report-style synthesis with explicit evidence use.<n>We propose a unified, interpretable evaluation pipeline: Formula-LLM Adaptive Evaluation (FLAE) for report quality, Trustworthy Retrieval-Aligned Citation Evaluation (TRACE) for citation-grounded evidence alignment, and Multimodal Support-Aligned Integrity Check (MOSAIC) for text-visual integrity.
  arXiv  Detail & Related papers  (2026-01-18T10:41:33Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports [24.09178055088843]
  Deep Research Agents (DRAs) exhibit the capabilities for task decomposition, cross-source retrieval, multi-stage reasoning, and structured output.<n>This paper introduces a rigorous benchmark and a multidimensional evaluation framework tailored to DRAs and report-style responses.<n>The framework enables comprehensive evaluation of long-form reports generated by DRAs, incorporating integrated scoring metrics for semantic quality, topical focus, and retrieval trustworthiness.
  arXiv  Detail & Related papers  (2025-10-02T16:40:02Z)
• Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework [22.366142327629486]
  Multimodal DeepResearcher decomposes the task into four stages: researching, report textualization, planning, and multimodal report generation.<n>It achieves an 82% overall win rate over the baseline method.
  arXiv  Detail & Related papers  (2025-06-03T05:18:19Z)

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.