2025/06/08 by Yuxuan Zheng, Zheng, Yangqing, Mao, Shunqi +4 · 2 citations
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #Embodied and Extended Cognition #FOS: Computer and information sciences #Machine Learning in Healthcare #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2506.07223
openalex publication_date 2025/06/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In the realm of embodied intelligence, the evolution of large language models (LLMs) has markedly enhanced agent decision making. Consequently, researchers have begun exploring agent performance in dynamically changing high-risk scenarios, i.e., fire, flood, and wind scenarios in the HAZARD benchmark. Under these extreme conditions, the delay in decision making emerges as a crucial yet insufficiently studied issue. We propose a Time Conversion Mechanism (TCM) that translates inference delays in decision-making into equivalent simulation frames, thus aligning cognitive and physical costs under a single FPS-based metric. By extending HAZARD with Respond Latency (RL) and Latency-to-Action Ratio (LAR), we deliver a fully latency-aware evaluation protocol. Moreover, we present the Rapid-Reflex Async-Reflect Agent (RRARA), which couples a lightweight LLM-guided feedback module with a rule-based agent to enable immediate reactive behaviors and asynchronous reflective refinements in situ. Experiments on HAZARD show that RRARA substantially outperforms existing baselines in latency-sensitive scenarios.