Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations

Emotional support conversation systems strive to emulate the empathetic depth of human therapists, yet current approaches often fail due to the "Cognitive Gap"-the inability to discern the latent psychological evaluations driving a user's distress. Existing retrieval-augmented generation paradigms exacerbate this by relying on semantic similarity, frequently retrieving historical dialogues that are surface analogous but therapeutically incongruent. To bridge this gap, we introduce Appraisal-Guided Chain-of-Thought Reasoning & Retrieval (AG-CTR 2 ) for better emotional support. Specifically, we bootstrap the MLLM to generate appraisalguided reasoning chains and apply a dualsignal verification mechanism using groundtruth emotion labels and a teacher model to verify and refine them. Under such instance-level guidance, we finetune the MLLM to internalize such reasoning capability. At inference, the model utilizes its generated appraisal chain as a structured query to help retrieve historical therapeutic responses based on psychological situation similarity rather than content surface proximity. Extensive experiments and analyses on two ESC benchmarks demonstrate that AG-CTR 2 significantly outperforms state-of-the-art baselines. Our data and codes are available. 1