Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity.Conventional LLMbased MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature homogenization.We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments that require long-horizon adaptability.By retaining partial diversity, systems can better explore novel strategies and cope with external shocks.We formalize a consensus-diversity tradeoff, showing conditions where implicit methods outperform explicit ones.Experiments on three scenarios -Dynamic Disaster Response, Information Spread and Manipulation, and Dynamic Public-Goods Provision -confirm partial deviation from group norms boosts exploration, robustness, and performance.We highlight emergent coordination via in-context learning, underscoring the value of preserving diversity for resilient decision-making.

This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and offering versatility in modeling various tasks. Our approach addresses three research questions: aligning LLMs with real-world urban mobility data, developing reliable activity generation strategies, and exploring LLM applications in urban mobility. The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation. We evaluate our LLM agent framework and compare it with state-of-the-art personal mobility generation approaches, demonstrating the effectiveness of our approach and its potential applications in urban mobility. Overall, this study marks the pioneering work of designing an LLM agent framework for activity generation based on real-world human activity data, offering a promising tool for urban mobility analysis.

Computational thinking (CT) skills are generally regarded as a basic ability for problem-solving and are gradually filtering down to younger age groups. Existing research has attempted to increase interaction and enhance the learning interest of elementary school students through block-based programming environments represented by Scratch. However, criticism suggests that this approach has potential long-term constraints on CT education. Therefore, this study designed a game-based project to investigate students’ learning motivation and CT performance in different programming environments. A total of 108 fifth-grade students participated in the experiment and were divided into two experimental groups (EG1 and EG2) and a control group (CG). The students in experimental groups all undertook game-based learning, while EG1 students used C++ and EG2 students used Scratch; CG students used C++ for traditional algorithm-based learning. Findings suggest that traditional programming languages with game-based learning can also substantially improve learning interest, which can promote the efficiency of improving CT for students who already have some motivation and foundation for learning. But for students who still lack motivation, are also encouraged to develop an interest in a block-based programming environment. Teachers can choose the most appropriate approach for students to find the best balance between learning efficiency and long-term interest.