EcoAct: Economic Agent Determines When to Register What Action

Shaokun Zhang, Jieyu Zhang, Dujian Ding, Mirian Del Carmen Hipolito Garcia, Ankur Mallick, Daniel Madrigal, Menglin Xia, Victor Rühle, Qingyun Wu, Chi Wang

Keywords: LLM, efficiency

Abstract:

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 incorporates all candidate tools into the agent’s context and retains 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 multi-step 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 universally applicable to LLM agents now and in the future.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 40