# EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.04623 · HTML: https://mlsanity.com/paper/2505.04623/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 7 May 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (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)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization](https://mlsanity.com/paper/2503.10615/) (2025)
- [MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning](https://mlsanity.com/paper/2503.07365/) (2025)
- [Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration](https://mlsanity.com/paper/2306.09093/) (2023)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)
- [OmniBench: Towards The Future of Universal Omni-Language Models](https://mlsanity.com/paper/2409.15272/) (2024)
- [R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning](https://mlsanity.com/paper/2503.05379/) (2025)
- [Audio-Visual LLM for Video Understanding](https://mlsanity.com/paper/2312.06720/) (2023)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models](https://mlsanity.com/paper/2310.05863/) (2023)
- [ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos](https://mlsanity.com/paper/2503.12542/) (2025)
- [Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization](https://mlsanity.com/paper/2502.01652/) (2025)

## Built on by (most cited first, 29 of 29)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context](https://mlsanity.com/paper/2506.21277/) (2025)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2505.18536/) (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)
- [Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding](https://mlsanity.com/paper/2604.11244/) (2026)
- [LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning](https://mlsanity.com/paper/2605.22012/) (2026)
- [XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models](https://mlsanity.com/paper/2510.15148/) (2025)
- [A Benchmark for Omni-Modal Reasoning in Long Videos](https://mlsanity.com/paper/2512.16978/) (2025)
- [OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering](https://mlsanity.com/paper/2602.03707/) (2026)
- [Native Active Perception as Reasoning for Omni-Modal Understanding](https://mlsanity.com/paper/2606.19341/) (2026)
- [Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning](https://mlsanity.com/paper/2602.11909/) (2026)
- [OmniReasoner: Thinking with Long Audio-Video via Native Tool Use](https://mlsanity.com/paper/2607.19339/) (2026)
- [FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design](https://mlsanity.com/paper/2506.13066/) (2025)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models](https://mlsanity.com/paper/2509.15661/) (2025)
- [Learning What to Attend First: Modality-Importance-Guided Reasoning for Reliable Multimodal Emotion Understanding](https://mlsanity.com/paper/2512.02699/) (2025)
- [Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs](https://mlsanity.com/paper/2604.05522/) (2026)
- [Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs](https://mlsanity.com/paper/2604.14520/) (2026)
- [AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers](https://mlsanity.com/paper/2604.16617/) (2026)
- [Reading Between the Frames of Multimodal Drivelology](https://mlsanity.com/paper/2608.04939/) (2026)
- [AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes](https://mlsanity.com/paper/2608.26193/) (2026)
- [Text-Centric Post-Training for Omni-Modal Reasoning](https://mlsanity.com/paper/2610.02819/) (2026)
- [OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning](https://mlsanity.com/paper/2610.12458/) (2026)
- [Omni-Modal LLMs Know More Than They Say](https://mlsanity.com/paper/2610.16135/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have advanced perception across text, vision, and audio, yet they often struggle with structured cross-modal reasoning, particularly when integrating audio and visual signals. We introduce EchoInk-R1, a reinforcement learning framework that enhances such reasoning in MLLMs. Built upon the Qwen2.5-Omni-7B foundation and optimized with Group Relative Policy Optimization (GRPO), EchoInk-R1 tackles multiple-choice question answering over synchronized audio-image pairs. To enable this, we curate AVQA-R1-6K, a dataset pairing such audio-image inputs with multiple-choice questions derived from OmniInstruct-v1. EchoInk-R1-7B achieves 85.77% accuracy on the validation set, outperforming the base model, which scores 80.53%, using only 562 reinforcement learning steps. Beyond accuracy, EchoInk-R1 demonstrates reflective reasoning by revisiting initial interpretations and refining responses when facing ambiguous multimodal inputs. These results suggest that lightweight reinforcement learning fine-tuning enhances cross-modal reasoning in MLLMs. EchoInk-R1 is the first framework to unify audio, visual, and textual modalities for general open-world reasoning via reinforcement learning. Code and data are publicly released to facilitate further research.