[2603.25031] From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support

Computer Science > Artificial Intelligence arXiv:2603.25031 (cs) [Submitted on 26 Mar 2026] Title:From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support Authors:Boning Zhao, Clover Hu, Xinnuo Li View a PDF of the paper titled From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support, by Boning Zhao and 2 other authors View PDF HTML (experimental) Abstract:In psychological support and emotional companionship scenarios, the core limitation of large language models (LLMs) lies not merely in response quality, but in their reliance on local next-token prediction, which prevents them from maintaining the temporal continuity, stage awareness, and user consent boundaries required for multi-turn intervention. This stateless characteristic makes systems prone to premature advancement, stage misalignment, and boundary violations in continuous dialogue. To address this problem, we argue that the key challenge in process-oriented emotional support is not simply generating natural language, but constructing a sustainably updatable external situational structure for the model. We therefore propose LEKIA 2.0, a situated LLM architecture that separates the cognitive layer from the executive layer, thereby decoupling situational modeling from intervention execution. This design enables the system to maintain stable representations of the user's situation and consent boundaries throughout ongoing interaction. To evaluate th...