{"ID":6536247,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10811","arxiv_id":"2607.10811","title":"Distributed Agent System: Fault-Tolerant Collaboration Among Embodied Agents","abstract":"AI engineering is shifting from passive text generation by large language models (LLMs) to agent-driven task execution, creating new reliability challenges for long-horizon tasks under resource constraints and environmental uncertainty. Conventional error-elimination optimization strategies fail to address cumulative error propagation. This paper proposes Distributed Agent System (DAS), a device-edge-cloud framework for fault-tolerant collaboration among heterogeneous agents. We redefine agent reliability as system-level fault tolerance rather than single-turn zero-error accuracy, and present a two-layer fault-tolerance architecture: single-agent execution reliability via fault-tolerant alignment, and cross-agent communication reliability via semi-formal language protocols. This framework provides a practical engineering pathway for reliable heterogeneous embodied agents collaboration in industrial scenarios.","short_abstract":"AI engineering is shifting from passive text generation by large language models (LLMs) to agent-driven task execution, creating new reliability challenges for long-horizon tasks under resource constraints and environmental uncertainty. Conventional error-elimination optimization strategies fail to address cumulative e...","url_abs":"https://arxiv.org/abs/2607.10811","url_pdf":"https://arxiv.org/pdf/2607.10811v1","authors":"[\"Kai Yu\",\"Lu Chen\",\"Hanqi Li\"]","published":"2026-07-12T15:45:54Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}