T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chakraborty, Amartya, Dashore, Paresh, Bathaee, Nadia, Jain, Anmol, Das, Anirban, Zhang, Shi-Xiong, Sahu, Sambit, Naphade, Milind, Winata, Genta Indra
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909866673569792
author Chakraborty, Amartya
Dashore, Paresh
Bathaee, Nadia
Jain, Anmol
Das, Anirban
Zhang, Shi-Xiong
Sahu, Sambit
Naphade, Milind
Winata, Genta Indra
author_facet Chakraborty, Amartya
Dashore, Paresh
Bathaee, Nadia
Jain, Anmol
Das, Anirban
Zhang, Shi-Xiong
Sahu, Sambit
Naphade, Milind
Winata, Genta Indra
contents Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving dependencies between API or tool calls-particularly in multi-turn conversations-remains a significant challenge. To address this, we introduce T1, a tool-augmented, multi-domain, multi-turn conversational dataset specifically designed to capture and manage inter-tool dependencies across diverse domains. T1 enables rigorous evaluation of agents' ability to coordinate tool use across nine distinct domains (4 single domain and 5 multi-domain) with the help of an integrated caching mechanism for both short- and long-term memory, while supporting dynamic replanning-such as deciding whether to recompute or reuse cached results. Beyond facilitating research on tool use and planning, T1 also serves as a benchmark for evaluating the performance of open-weight and proprietary large language models. We present results powered by T1-Agent, highlighting their ability to plan and reason in complex, tool-dependent scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16986
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
Chakraborty, Amartya
Dashore, Paresh
Bathaee, Nadia
Jain, Anmol
Das, Anirban
Zhang, Shi-Xiong
Sahu, Sambit
Naphade, Milind
Winata, Genta Indra
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving dependencies between API or tool calls-particularly in multi-turn conversations-remains a significant challenge. To address this, we introduce T1, a tool-augmented, multi-domain, multi-turn conversational dataset specifically designed to capture and manage inter-tool dependencies across diverse domains. T1 enables rigorous evaluation of agents' ability to coordinate tool use across nine distinct domains (4 single domain and 5 multi-domain) with the help of an integrated caching mechanism for both short- and long-term memory, while supporting dynamic replanning-such as deciding whether to recompute or reuse cached results. Beyond facilitating research on tool use and planning, T1 also serves as a benchmark for evaluating the performance of open-weight and proprietary large language models. We present results powered by T1-Agent, highlighting their ability to plan and reason in complex, tool-dependent scenarios.
title T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.16986