OmniGAIA: Towards Native Omni-Modal AI Agents
This work addresses the limitation of current multi-modal LLMs, which are primarily bi-modal, by providing a benchmark and an agent for developing more unified cognitive AI assistants capable of omni-modal perception and reasoning.
This paper introduces OmniGAIA, a benchmark for evaluating AI agents on tasks requiring deep reasoning and multi-turn tool execution across video, audio, and image modalities. It also proposes OmniAtlas, a native omni-modal foundation agent that enhances tool-use capabilities of existing open-source models through active omni-modal perception and a hindsight-guided tree exploration strategy.
Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel omni-modal event graph approach, OmniGAIA synthesizes complex, multi-hop queries derived from real-world data that require cross-modal reasoning and external tool integration. Furthermore, we propose OmniAtlas, a native omni-modal foundation agent under tool-integrated reasoning paradigm with active omni-modal perception. Trained on trajectories synthesized via a hindsight-guided tree exploration strategy and OmniDPO for fine-grained error correction, OmniAtlas effectively enhances the tool-use capabilities of existing open-source models. This work marks a step towards next-generation native omni-modal AI assistants for real-world scenarios.