Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yu, Peijie, Yang, Yifan, Li, Jinjian, Zhang, Zelong, Wang, Haorui, Feng, Xiao, Zhang, Feng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.02623
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912330454925312
author Yu, Peijie
Yang, Yifan
Li, Jinjian
Zhang, Zelong
Wang, Haorui
Feng, Xiao
Zhang, Feng
author_facet Yu, Peijie
Yang, Yifan
Li, Jinjian
Zhang, Zelong
Wang, Haorui
Feng, Xiao
Zhang, Feng
contents Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the proposed benchmark explores all possible mission-switching patterns within a fixed mission number. Specifically, we propose a multi-agent data generation framework to construct the benchmark. We also propose a novel method to evaluate the accuracy and efficiency of agent decisions with dynamic decision trees. Experiments on diverse open-source and closed-source LLMs reveal critical factors influencing agent robustness and provide actionable insights to the tool invocation society.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02623
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
Yu, Peijie
Yang, Yifan
Li, Jinjian
Zhang, Zelong
Wang, Haorui
Feng, Xiao
Zhang, Feng
Artificial Intelligence
Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the proposed benchmark explores all possible mission-switching patterns within a fixed mission number. Specifically, we propose a multi-agent data generation framework to construct the benchmark. We also propose a novel method to evaluate the accuracy and efficiency of agent decisions with dynamic decision trees. Experiments on diverse open-source and closed-source LLMs reveal critical factors influencing agent robustness and provide actionable insights to the tool invocation society.
title Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
topic Artificial Intelligence
url https://arxiv.org/abs/2504.02623