EcoAct：经济型智能体决定何时注册什么动作
EcoAct: Economic Agent Determines When to Register What Action
AI总结：
EcoAct通过将工具注册整合进推理流程，使LLM智能体按需选择性注册工具，降低计算成本超50%并保持性能，且可即插即用。
摘要：
近期进展使大型语言模型（LLMs）能够作为智能体，利用外部工具执行动作。这要求在采取动作之前进行注册，即将工具信息整合到LLM上下文中。当前方法不加区分地将所有候选工具纳入智能体上下文，并在多个推理步骤中保留它们。此过程对LLM智能体而言不透明，且未整合进其推理流程，导致因无关工具增加上下文长度而产生低效。为解决此问题，我们提出EcoAct，一种工具使用算法，允许LLM按需选择性注册工具，优化上下文使用。通过将工具注册过程整合进推理流程，EcoAct在多项步骤推理任务中将计算成本降低超过50%，同时保持性能，这通过广泛实验得到验证。此外，它可插入任何推理流程，仅需对提示进行少量修改，因此适用于当前及未来的LLM智能体。
英文摘要：
Recent advancements have enabled Large Language Models (LLMs) to function as agents that can perform actions using external tools. This requires registering, i.e., integrating tool information into the LLM context prior to taking actions. Current methods indiscriminately incorporate all candidate tools into the agent's context and retain them across multiple reasoning steps. This process remains opaque to LLM agents and is not integrated into their reasoning procedures, leading to inefficiencies due to increased context length from irrelevant tools. To address this, we introduce EcoAct, a tool using algorithm that allows LLMs to selectively register tools as needed, optimizing context use. By integrating the tool registration process into the reasoning procedure, EcoAct reduces computational costs by over 50% in multiple steps reasoning tasks while maintaining performance, as demonstrated through extensive experiments. Moreover, it can be plugged into any reasoning pipeline with only minor modifications to the prompt, making it applicable to LLM agents now and future.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
