SMART: Self-Aware Agent for Tool Overuse Mitigation

• URL: http://arxiv.org/abs/2502.11435v1
• Date: Mon, 17 Feb 2025 04:50:37 GMT
• Title: SMART: Self-Aware Agent for Tool Overuse Mitigation
• Authors: Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji,
• Abstract summary: Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness. This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks with parametric knowledge. We introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse.
• Score: 58.748554080273585
• License:
• Abstract: Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks solvable with parametric knowledge, increasing computational overhead. Inspired by human metacognition, we introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse. To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary. Through supervised training, we develop SMARTAgent, a family of models that dynamically balance parametric knowledge and tool use. Evaluations show that SMARTAgent reduces tool use by 24% while improving performance by over 37%, enabling 7B-scale models to match its 70B counterpart and GPT-4o. Additionally, SMARTAgent generalizes to out-of-distribution test data like GSM8K and MINTQA, maintaining accuracy with just one-fifth the tool calls. These highlight the potential of strategic tool use to enhance reasoning, mitigate overuse, and bridge the gap between model size and performance, advancing intelligent and resource-efficient agent designs.

Related papers

• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use. MeCo captures high-level cognitive signals in the representation space, guiding when to invoke tools. Our experiments show that MeCo accurately detects LLMs' internal cognitive signals and significantly improves tool-use decision-making.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)
• LLM Agents Making Agent Tools [2.5529148902034637]
  Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks. We propose ToolMaker, a novel agentic framework that autonomously transforms papers with code into LLM-compatible tools. Given a short task description and a repository URL, ToolMaker autonomously installs required dependencies and generates code to perform the task.
  arXiv  Detail & Related papers  (2025-02-17T11:44:11Z)
• SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration [24.739131794947838]
  We conduct a study on a family of state-of-the-art Large Language Models (LLMs) on three datasets with two mainstream tool-use frameworks. Our study reveals the tool-abuse behavior of LLMs, a tendency for models to misuse tools with overconfidence. We propose a novel approach, textitCAL, to mitigate the observed issues.
  arXiv  Detail & Related papers  (2024-12-11T06:09:12Z)
• Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases [0.0]
  We introduce Toolshed Knowledge Bases, a tool knowledge base (vector database) designed to store enhanced tool representations. We also propose Advanced RAG-Tool Fusion, a novel ensemble of tool-applied advanced retrieval-augmented generation (RAG) techniques. Our approach achieves 46%, 56%, and absolute improvements on the ToolE single-tool, ToolE multi-tool and Seal-Tools benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-18T16:44:22Z)
• MetaTool: Facilitating Large Language Models to Master Tools with Meta-task Augmentation [25.360660222418183]
  We present MetaTool, a novel tool learning methodology designed to generalize across any reusable toolset. By incorporating meta-task data into task-oriented training, our method significantly enhances the performance of open-source Large Language Models.
  arXiv  Detail & Related papers  (2024-07-15T10:15:41Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)
• Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning [56.82041895921434]
  Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities. When used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2024-03-29T03:48:12Z)
• Tool-Augmented Reward Modeling [58.381678612409]
  We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
  arXiv  Detail & Related papers  (2023-10-02T09:47:40Z)
• Large Language Models as Tool Makers [85.00361145117293]
  We introduce a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving. Our approach consists of two phases: 1) tool making: an LLM acts as the tool maker that crafts tools for a set of tasks. 2) tool using: another LLM acts as the tool user, which applies the tool built by the tool maker for problem-solving.
  arXiv  Detail & Related papers  (2023-05-26T17:50:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.