Communication Policy Evolution for Proactive LLM Agents
让LLM代理从被动响应转向主动交互,通信策略演化是关键突破。
arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains betw…
让LLM代理从被动响应转向主动交互,通信策略演化是关键突破。
arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains betw…
基于置信度驱动的MLLM移动代理,在不确定性下实现主动且鲁棒的用户交互,前沿研究突破。
arXiv:2605.28629v1 Announce Type: new Abstract: Recent advancements in multimodal large language models (MLLMs) have shown exceptional potential in en…
首个主动式视频大模型,实时理解视频并主动发起对话,开启AI伴侣交互新范式
arXiv:2603.03447v3 Announce Type: replace Abstract: Proactive and real-time interactive experiences are essential for human-like AI companions, yet fa…
突破现有强化学习局限,提出通过主动交互提升大模型推理能力的新方法。
arXiv:2605.08401v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have demonstrated remarkable reasoning capab…