paper-with-me

Papers

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

2025-05-12 · Xu Huang, Weiwen Liu, Xingshan Zeng, Yuefeng Huang, Xinlong Hao, Yuxian Wang, Yirong Zeng, Chuhan Wu, Yasheng Wang, Ruiming Tang, Defu Lian

The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data synthesis. However, this method incurs significant costs associated with advanced model usage and often results in data compatibility issues, led by the high discrepancy in the knowledge scope between the advanced model and the target model. To address these challenges, we propose ToolACE-DEV, a self-improving framework for tool learning. First, we decompose the tool-learning objective into sub-tasks that enhance basic tool-making and tool-using abilities. Then, we introduce a self-evolving paradigm that allows lightweight models to self-improve, reducing reliance on advanced LLMs. Extensive experiments validate the effectiveness of our approach across models of varying scales and architectures.

📄 PDF Abstract BibTeX arXiv:2505.07512

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ToolACE: Winning the Points of LLM Function Calling

2024-09-02 · Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao 외

Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is qui…

ToolACE-R: Tool Learning with Adaptive Self-Refinement

2025-04-02 · Xingshan Zeng, Weiwen Liu, Xu Huang, Zezhong Wang 외

Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, current approaches primaril…

Computational Efficiency

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction

2025-08-18 · Xingshan Zeng, Weiwen Liu, Lingzhi Wang, Liangyou Li 외 arxiv

Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions, often involving complex function calls and dynamic user-agent exchanges. Existing simulation-based data generation meth…

IntentMiner: Intent Inversion Attack via Tool Call Analysis in the Model Context Protocol

2025-12-16 · Yunhao Yao, Zhiqiang Wang, Haoran Cheng, Yihang Cheng 외 arxiv

The evolution of Large Language Models (LLMs) into Agentic AI has established the Model Context Protocol (MCP) as the standard for connecting reasoning engines with external tools. Although this decoupled architecture fo…

Semantic Parsing

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents

2026-01-13 · Yiting Shen, Kun Li, Wei Zhou, Songlin Hu arxiv

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to pa…