OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering. OmniReasoner first builds a low-cost global preview of the full stream and then, when needed, calls the zoom-in tool with a requested temporal interval for higher-fideli
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%Developer-Y/cs-video-courses →
“Fuzzy title match (0.73): “OmniReasoner: Thinking with Long Audio-Video via Native Tool” ≈ “Developer-Y/cs-video-courses””
- LinkedLinked via arxiv author · 85%Xuanyu Chen →
“OmniReasoner: Thinking with Long Audio-Video via Native Tool Use”
- LinkedLinked via arxiv author · 85%Caorui Li →
“OmniReasoner: Thinking with Long Audio-Video via Native Tool Use”
- LinkedLinked via arxiv author · 85%Ziyu Xiong →
“OmniReasoner: Thinking with Long Audio-Video via Native Tool Use”
- LinkedLinked via arxiv author · 85%Yidong Wang →
“OmniReasoner: Thinking with Long Audio-Video via Native Tool Use”