{"ID":2885187,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05298","arxiv_id":"2508.05298","title":"GhostShell: Streaming LLM Function Calls for Concurrent Embodied Programming","abstract":"We present GhostShell, a novel approach that leverages Large Language Models (LLMs) to enable streaming and concurrent behavioral programming for embodied systems. In contrast to conventional methods that rely on pre-scheduled action sequences or behavior trees, GhostShell drives embodied systems to act on-the-fly by issuing function calls incrementally as tokens are streamed from the LLM. GhostShell features a streaming XML function token parser, a dynamic function interface mapper, and a multi-channel scheduler that orchestrates intra-channel synchronous and inter-channel asynchronous function calls, thereby coordinating serial-parallel embodied actions across multiple robotic components under LLM guidance. We evaluate GhostShell on our robotic prototype COCO through comprehensive grounded experiments across 34 real-world interaction tasks and multiple LLM backends. The results demonstrate that our approach achieves a state-of-the-art Behavioral Correctness Metric of 0.85 with Claude-4-Sonnet, and up to 66X faster response times compared to native LLM function calling APIs. GhostShell also proves effective in long-horizon multimodal tasks, exhibiting strong robustness and generalization capabilities.","short_abstract":"We present GhostShell, a novel approach that leverages Large Language Models (LLMs) to enable streaming and concurrent behavioral programming for embodied systems. In contrast to conventional methods that rely on pre-scheduled action sequences or behavior trees, GhostShell drives embodied systems to act on-the-fly by i...","url_abs":"https://arxiv.org/abs/2508.05298","url_pdf":"https://arxiv.org/pdf/2508.05298v2","authors":"[\"Jian Gong\",\"Youwei Huang\",\"Bo Yuan\",\"Ming Zhu\",\"Zhou Liao\",\"Jianhang Liang\",\"Juncheng Zhan\",\"Jinke Wang\",\"Hang Shu\",\"Mingyue Xiong\",\"Yanjun Ye\",\"Yufan Zu\",\"Yang Zhou\",\"Yihan Ding\",\"Xuannian Chen\",\"Xingyu Lu\",\"Runjie Ban\",\"Bingchao Huang\",\"Fusen Liu\"]","published":"2025-08-07T11:55:46Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}