paper-with-me

Papers

AutoTool: Efficient Tool Selection for Large Language Model Agents

2025-11-18 · Jingyi Jia, Qinbin Li arxiv

Large Language Model (LLM) agents have emerged as powerful tools for automating complex tasks by leveraging the reasoning and decision-making abilities of LLMs. However, a major bottleneck in current agent frameworks lies in the high inference cost of tool selection, especially in approaches like ReAct that repeatedly invoke the LLM to determine which tool to use at each step. In this work, we propose AutoTool, a novel graph-based framework that bypasses repeated LLM inference by exploiting a key empirical observation: tool usage inertia - the tendency of tool invocations to follow predictable sequential patterns. AutoTool constructs a directed graph from historical agent trajectories, where nodes represent tools and edges capture transition probabilities, effectively modeling the inertia in tool selection. It further integrates parameter-level information to refine tool input generation. By traversing this structured representation, AutoTool efficiently selects tools and their parameters with minimal reliance on LLM inference. Extensive experiments across diverse agent tasks demonstrate that AutoTool reduces inference costs by up to 30% while maintaining competitive task completion rates, offering a practical and scalable enhancement for inference-heavy frameworks. Our work highlights the promise of integrating statistical structure into LLM agent design for greater efficiency without sacrificing performance.

📄 PDF Abstract BibTeX arXiv:2511.14650

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning

2025-12-15 · Jiaru Zou, Ling Yang, Yunzhe Qi, Sirui Chen 외 arxiv

Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use. Existing approaches assume a fixed inventory of tools, w…

Reinforcement LearningMultimodal ReasoningCode Generation

Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning

2026-05-19 · Qinghe Ma, Zhen Zhao, Yiming Wu, Jian Zhang 외 arxiv

Tool-augmented reasoning has emerged as a promising direction for enhancing the reasoning capabilities of multimodal large language models (MLLMs). However, existing studies mainly focus on enabling models to perform too…

Reinforcement Learning

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints

2026-03-07 · Yirong Zeng, Xiao Ding, Yufei Liu, Yuxian Wang 외 arxiv

Tool use represents a critical capability for AI agents, with recent advances focusing on leveraging reinforcement learning (RL) to scale up the explicit reasoning process to achieve better performance. However, there ar…

Reinforcement Learning

Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments

2025-09-22 · Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj arxiv

We present Dynamic ReAct, a novel approach for enabling ReAct agents to efficiently operate with extensive Model Control Protocol (MCP) tool sets that exceed the contextual memory limitations of large language models. Ou…

JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents

2026-04-20 · Sandip Ghoshal, Anshul Mittal, Jyotika Singh, Miguel Ballesteros 외 arxiv

Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptions and under-specified agent instruction…

Slot Filling