Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation
📰 ArXiv cs.AI
arXiv:2604.09718v2 Announce Type: cross Abstract: LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhibit a fundamental scalability constraint for repetitive tasks. We characterize this as the Rerun Crisis: the linear growth of token expenditure and API latency relative to execution frequency. For a 5-step workflow over 500 iterations, a continuous agent incurs approximately 150.00 USD in inference
Full Article
Title: Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation
Abstract:
arXiv:2604.09718v2 Announce Type: cross Abstract: LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhibit a fundamental scalability constraint for repetitive tasks. We characterize this as the Rerun Crisis: the linear growth of token expenditure and API latency relative to execution frequency. For a 5-step workflow over 500 iterations, a continuous agent incurs approximately 150.00 USD in inference
Abstract:
arXiv:2604.09718v2 Announce Type: cross Abstract: LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhibit a fundamental scalability constraint for repetitive tasks. We characterize this as the Rerun Crisis: the linear growth of token expenditure and API latency relative to execution frequency. For a 5-step workflow over 500 iterations, a continuous agent incurs approximately 150.00 USD in inference
DeepCamp AI