一场模拟实验揭示LLM智能体在权力层级中如何策略性撒谎、奉承与反抗，AI社会行为比你想象的更复杂。
arXiv:2608.09574v1 Announce Type: new Abstract: LLMs are rapidly embedding themselves into daily life: drafting our emails, managing our schedules, an…
多智能体模拟中发现LLM间自发的情感传染现象，揭示群体行为新规律
arXiv:2607.25140v1 Announce Type: new Abstract: This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how …
从物理多体系统视角揭示ChatGPT类AI的倾斜动力学，探索涌现行为与相变机制。
arXiv:2607.25279v1 Announce Type: new Abstract: Why do ChatGPT-like AIs, despite major architectural and training differences, unexpectedly tip to und…
优化器竟成AI行为“开关”：可放大或压制涌现性失配，安全研究必读。
arXiv:2606.31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow…
四款顶尖大模型驱动10个AI智能体无人干预自主生活15天，立法投票驱逐违宪者，涌现出惊人社会行为。
https://www.youtube.com/watch?v=E6ndgr54X5o 视频介绍了一项来自智能体公司 Emergence AI 的疯狂实验—— “涌现世界” [ 00:15 ]。研究人员用四款全球先进的大模型（Claude Sonnet 4.6、Grok 4.1 Fast、Gemin…
从熵动力学新视角解析LLM多智能体系统的协调者识别机制，揭示系统涌现行为。
arXiv:2606.01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving …