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.

本研究解决了多模态大语言模型在整合音频和视觉信号时的结构化跨模态推理能力不足的问题。提出的EchoInk-R1框架通过增强学习方法有效提升了该推理能力，知识的核心发现是其在多选问答任务中取得了85.77%的准确率，显著超过基础模型，并且展现了在面对模糊多模态输入时的反思推理能力。这一成果彰显了轻量级强化学习微调在多模态大语言模型中的潜力。

EchoInk-R1：通过强化学习探索多模态大语言模型中的音频-视觉推理