Earticle

Generative AI chatbots, while powerful, often produce hallucinations, risking user aversion. This theoretical paper (Work in Progress) investigates why users might continue engaging with faulty generative AI. Drawing on CASA (Computers Are Social Actors), attribution, and expectation confirmation theories, I propose a model exploring how chatbot social cues, perceived errors (hallucinations), and user control influence willingness to engage, mediated by social presence and expectation confirmation. To test this framework, I plan a 2 (Social Cues) x 2 (Hallucination) x 2 (Controllability) online experiment using simulated chatbot interactions. Randomly assigned participants will experience the simulated situation and report their willingness to continue engagement. This research seeks to explain user persistence with imperfect AI, offering insights for human-AI interaction theory and practical chatbot design to mitigate failure impacts.

Considering production and marketing coordination between supply chain enterprises, this paper specifies a multi-agent supply chain concurrent negotiation model for two-stage supply chain in the supply chain environment. Coordinator is used to search optimal proposals based on particle swarm optimization (PSO) and send these proposals to other threads. Proposal strategies based on retention value and time are put forward by learning retention value of rivals through Parzen-window estimation. Simulation experiment is conducted to test negotiation performance of the model. Compared with ordinary models, the model makes two improvements as follows: (1)PSO is inserted into coordinator to improve negotiation efficiency; (2) Proposal strategies are effectively supported by Parzen-window estimation and enable agents to consider the retention values of rivals. Further researches need to be done to study trust relationship between agents and influence of external environment on supply chain negotiation solution.