EChO-Agent: Evidence Chain Orchestration Agent for Audio Reasoning
For researchers working on audio reasoning, this work addresses the lack of focus on question-relevant segments and checkable reasoning in LALMs.
EChO-Agent improves audio question answering by reformulating it as a planning, tool execution, evidence integration, and verification workflow, achieving higher accuracy and rubric scores on the MMAR benchmark.
While LALMs show promise on audio question answering, they fail to focus on question-relevant segments of audio and provide a clear, checkable reasoning process when dealing with complex audio reasoning. Reinforcement learning and tool-augmented prompting can help models better relate questions to audio but lack a reliable way to understand, integrate, and self-verify audio segments. To address this gap, we present EChO-Agent, a modular agent framework that reformulates complex audio QA as a planning, tool execution, evidence integration, and answer verification workflow. Experiments on MMAR benchmark show EChO-Agent improves both accuracy and rubric scores over baseline and ablation studies show evidence integration is the key factor.