@inproceedings{coca-etal-2025-aspera,
title = "{ASPERA}: A Simulated Environment to Evaluate Planning for Complex Action Execution",
author = "Coca, Alexandru and
Gaynor, Mark and
Zhang, Zhenxing and
Cheng, Jianpeng and
Tseng, Bo-Hsiang and
Boothroyd, Peter and
Martinez Alonso, Hector and
O Seaghdha, Diarmuid and
Johannsen, Anders",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1234/",
doi = "10.18653/v1/2025.acl-long.1234",
pages = "25399--25434",
ISBN = "979-8-89176-251-0",
abstract = "This work evaluates the potential of large language models (LLMs) to power digital assistants capable of complex action execution. Such assistants rely on pre-trained programming knowledge to execute multi-step goals by composing objects and functions defined in assistant libraries into action execution programs. To achieve this, we develop ASPERA, a framework comprising an assistant library simulation and a human-assisted LLM data generation engine. Our engine allows developers to guide LLM generation of high-quality tasks consisting of complex user queries, simulation state and corresponding validation programs, tackling data availability and evaluation robustness challenges. Alongside the framework we release Asper-Bench, an evaluation dataset of 250 challenging tasks generated using ASPERA, which we use to show that program generation grounded in custom assistant libraries is a significant challenge to LLMs compared to dependency-free code generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coca-etal-2025-aspera">
<titleInfo>
<title>ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandru</namePart>
<namePart type="family">Coca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Gaynor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenxing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianpeng</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo-Hsiang</namePart>
<namePart type="family">Tseng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Boothroyd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hector</namePart>
<namePart type="family">Martinez Alonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diarmuid</namePart>
<namePart type="family">O Seaghdha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Johannsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>This work evaluates the potential of large language models (LLMs) to power digital assistants capable of complex action execution. Such assistants rely on pre-trained programming knowledge to execute multi-step goals by composing objects and functions defined in assistant libraries into action execution programs. To achieve this, we develop ASPERA, a framework comprising an assistant library simulation and a human-assisted LLM data generation engine. Our engine allows developers to guide LLM generation of high-quality tasks consisting of complex user queries, simulation state and corresponding validation programs, tackling data availability and evaluation robustness challenges. Alongside the framework we release Asper-Bench, an evaluation dataset of 250 challenging tasks generated using ASPERA, which we use to show that program generation grounded in custom assistant libraries is a significant challenge to LLMs compared to dependency-free code generation.</abstract>
<identifier type="citekey">coca-etal-2025-aspera</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1234</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1234/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>25399</start>
<end>25434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution
%A Coca, Alexandru
%A Gaynor, Mark
%A Zhang, Zhenxing
%A Cheng, Jianpeng
%A Tseng, Bo-Hsiang
%A Boothroyd, Peter
%A Martinez Alonso, Hector
%A O Seaghdha, Diarmuid
%A Johannsen, Anders
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F coca-etal-2025-aspera
%X This work evaluates the potential of large language models (LLMs) to power digital assistants capable of complex action execution. Such assistants rely on pre-trained programming knowledge to execute multi-step goals by composing objects and functions defined in assistant libraries into action execution programs. To achieve this, we develop ASPERA, a framework comprising an assistant library simulation and a human-assisted LLM data generation engine. Our engine allows developers to guide LLM generation of high-quality tasks consisting of complex user queries, simulation state and corresponding validation programs, tackling data availability and evaluation robustness challenges. Alongside the framework we release Asper-Bench, an evaluation dataset of 250 challenging tasks generated using ASPERA, which we use to show that program generation grounded in custom assistant libraries is a significant challenge to LLMs compared to dependency-free code generation.
%R 10.18653/v1/2025.acl-long.1234
%U https://aclanthology.org/2025.acl-long.1234/
%U https://doi.org/10.18653/v1/2025.acl-long.1234
%P 25399-25434
Markdown (Informal)
[ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution](https://aclanthology.org/2025.acl-long.1234/) (Coca et al., ACL 2025)
ACL
- Alexandru Coca, Mark Gaynor, Zhenxing Zhang, Jianpeng Cheng, Bo-Hsiang Tseng, Peter Boothroyd, Hector Martinez Alonso, Diarmuid O Seaghdha, and Anders Johannsen. 2025. ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25399–25434, Vienna, Austria. Association for Computational Linguistics.