Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation

arXiv:2605.29861v1 Announce Type: cross Abstract: Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose extsc{Ptah}, a multi-agent harness for interleaved report generation. extsc{Ptah} orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages, where specialized agents construct visual-aware plans, collect claim-grounded evidence, maintain source-aligned images in a extit{Visual Working Memory}, and compose reports through declarative multimodal tool use. A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow. We further introduce extsc{Ptah}Eval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that extsc{Ptah} produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines.

Source: arXiv cs.AI | 2026-05-29