# Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

arXiv: https://arxiv.org/abs/2505.20256 · HTML: https://mlsanity.com/paper/2505.20256/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 64 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 30 of 54)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding](https://mlsanity.com/paper/2306.17107/) (2023)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)

## Built on by (most cited first, 30 of 41)

- [LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling](https://mlsanity.com/paper/2511.20785/) (2025)
- [ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning](https://mlsanity.com/paper/2505.21457/) (2025)
- [Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models](https://mlsanity.com/paper/2508.09138/) (2025)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [OmniGAIA: Towards Native Omni-Modal AI Agents](https://mlsanity.com/paper/2602.22897/) (2026)
- [Reinforcing Video Reasoning Segmentation to Think Before It Segments](https://mlsanity.com/paper/2508.11538/) (2025)
- [AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video](https://mlsanity.com/paper/2508.03100/) (2025)
- [OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention](https://mlsanity.com/paper/2602.05847/) (2026)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning](https://mlsanity.com/paper/2601.09536/) (2026)
- [Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding](https://mlsanity.com/paper/2604.11244/) (2026)
- [ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding](https://mlsanity.com/paper/2602.23306/) (2026)
- [XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models](https://mlsanity.com/paper/2510.15148/) (2025)
- [OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering](https://mlsanity.com/paper/2602.03707/) (2026)
- [Improving Visual Reasoning with Iterative Evidence Refinement](https://mlsanity.com/paper/2603.14117/) (2026)
- [GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert](https://mlsanity.com/paper/2510.03896/) (2025)
- [MARBLE: Multi-Aspect Reward Balance for Diffusion RL](https://mlsanity.com/paper/2605.06507/) (2026)
- [Watch, Remember, Reason: Human-View Video Understanding with MLLMs](https://mlsanity.com/paper/2606.07433/) (2026)
- [Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning](https://mlsanity.com/paper/2510.11454/) (2025)
- [OmniReasoner: Thinking with Long Audio-Video via Native Tool Use](https://mlsanity.com/paper/2607.19339/) (2026)
- [X3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment](https://mlsanity.com/paper/2607.21550/) (2026)
- [CMDAR: A Chinese Multi-scene Dynamic Audio Reasoning Benchmark with Diverse Challenges](https://mlsanity.com/paper/2509.22461/) (2025)
- [ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning](https://mlsanity.com/paper/2512.18571/) (2025)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models](https://mlsanity.com/paper/2608.22236/) (2026)
- [R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios](https://mlsanity.com/paper/2511.16901/) (2025)
- [Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs](https://mlsanity.com/paper/2604.05522/) (2026)
- [OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering](https://mlsanity.com/paper/2604.08209/) (2026)
- [Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs](https://mlsanity.com/paper/2604.14520/) (2026)

## Abstract (arXiv)

Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution inputs. We tackle this trade-off with a two-system architecture: a Global Reasoning System selects informative keyframes and rewrites the task at low spatial cost, while a Detail Understanding System performs pixel-level grounding on the selected high-resolution snippets. Because ``optimal'' keyframe selection and reformulation are ambiguous and hard to supervise, we formulate them as a reinforcement learning (RL) problem and present Omni-R1, an end-to-end RL framework built on Group Relative Policy Optimization. Omni-R1 trains the Global Reasoning System through hierarchical rewards obtained via online collaboration with the Detail Understanding System, requiring only one epoch of RL on small task splits. Experiments on two challenging benchmarks, namely Referring Audio-Visual Segmentation (RefAVS) and Reasoning Video Object Segmentation (REVOS), show that Omni-R1 not only surpasses strong supervised baselines but also outperforms specialized state-of-the-art models, while substantially improving out-of-domain generalization and mitigating multimodal hallucination. Our results demonstrate the first successful application of RL to large-scale omnimodal reasoning and highlight a scalable path toward universally foundation models.