# Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search

arXiv: https://arxiv.org/abs/2605.08762 · HTML: https://mlsanity.com/paper/2605.08762/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 22 of 22)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [MiMo-V2-Flash Technical Report](https://mlsanity.com/paper/2601.02780/) (2026)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs](https://mlsanity.com/paper/2502.04326/) (2025)
- [WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent](https://mlsanity.com/paper/2508.05748/) (2025)
- [Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities](https://mlsanity.com/paper/2505.17862/) (2025)
- [AVID: Any-Length Video Inpainting with Diffusion Model](https://mlsanity.com/paper/2312.03816/) (2023)
- [AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?](https://mlsanity.com/paper/2412.02611/) (2024)
- [OmniGAIA: Towards Native Omni-Modal AI Agents](https://mlsanity.com/paper/2602.22897/) (2026)
- [MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline](https://mlsanity.com/paper/2603.01050/) (2026)
- [Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning](https://mlsanity.com/paper/2601.06943/) (2026)
- [UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models](https://mlsanity.com/paper/2510.18915/) (2025)
- [DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models](https://mlsanity.com/paper/2601.19267/) (2026)
- [Video-Browser: Towards Agentic Open-web Video Browsing](https://mlsanity.com/paper/2512.23044/) (2025)
- [Do Audio-Visual Large Language Models Really See and Hear?](https://mlsanity.com/paper/2604.02605/) (2026)
- [Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention](https://mlsanity.com/paper/2603.27187/) (2026)
- [OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video](https://mlsanity.com/paper/2604.11102/) (2026)
- [Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness](https://mlsanity.com/paper/2504.16936/) (2025)
- [OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models](https://mlsanity.com/paper/2603.23938/) (2026)

## Built on by (most cited first, 1 of 1)

- [EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards](https://mlsanity.com/paper/2608.23525/) (2026)

## Abstract (arXiv)

Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively search for cross-modal evidence remains underexplored. In this paper, we introduce Omni-DeepSearch, a benchmark for audio-driven omni-modal deep search. Given one or more audio clips and a related question, models must infer useful clues from audio, invoke text, image, and video search tools, and perform multi-hop reasoning to produce a short, objective, and verifiable answer. Omni-DeepSearch contains 640 samples across 15 fine-grained categories, covering four retrieval target modalities and four audio content types. A multi-stage filtering pipeline ensures audio dependence, retrieval necessity, visual modality necessity, and answer uniqueness. Experiments on recent closed-source and open-source omni-modal models show that this task remains highly challenging: the strongest evaluated model, Gemini-3-Pro, achieves only 43.44% average accuracy. Further analyses illustrate key bottlenecks in audio entity inference, query formulation, tool-use reliability, multi-hop retrieval, and cross-modal verification. These results highlight audio-driven omni-modal deep search as an important and underexplored direction for future multimodal agents.