{"ID":2826346,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19551","arxiv_id":"2512.19551","title":"Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios","abstract":"In the literature, existing human-centric emotional motion generation methods primarily focus on boosting performance within a single scale-fixed dataset, largely neglecting the flexible and scale-increasing motion scenarios (e.g., sports, dance), whereas effectively learning these newly emerging scenarios can significantly enhance the model's real-world generalization ability. Inspired by this, this paper proposes a new LLM-Centric Lifelong Empathic Motion Generation (L^2-EMG) task, which aims to equip LLMs with the capability to continually acquire emotional motion generation knowledge across different unseen scenarios, potentially contributing to building a closed-loop and self-evolving embodied agent equipped with both empathy and intelligence. Further, this paper poses two key challenges in the L^2-EMG task, i.e., the emotion decoupling challenge and the scenario adapting challenge. To this end, this paper proposes an Emotion-Transferable and Scenario-Adapted Mixture of Experts (ES-MoE) approach which designs a causal-guided emotion decoupling block and a scenario-adapted expert constructing block to address the two challenges, respectively. Especially, this paper constructs multiple L^2-EMG datasets to validate the effectiveness of the ES-MoE approach. Extensive evaluations show that ES-MoE outperforms advanced baselines.","short_abstract":"In the literature, existing human-centric emotional motion generation methods primarily focus on boosting performance within a single scale-fixed dataset, largely neglecting the flexible and scale-increasing motion scenarios (e.g., sports, dance), whereas effectively learning these newly emerging scenarios can signific...","url_abs":"https://arxiv.org/abs/2512.19551","url_pdf":"https://arxiv.org/pdf/2512.19551v1","authors":"[\"Jiawen Wang\",\"Jingjing Wang Tianyang Chen\",\"Min Zhang\",\"Guodong Zhou\"]","published":"2025-12-22T16:31:30Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Mixture of Experts\",\"Large Language Model\"]","has_code":false}