@inproceedings{chen-etal-2025-atlas,
title = "{ATLAS}: Agent Tuning via Learning Critical Steps",
author = "Chen, Zhixun and
Li, Ming and
Huang, Yuxuan and
Du, Yali and
Fang, Meng and
Zhou, Tianyi",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1299/",
doi = "10.18653/v1/2025.findings-acl.1299",
pages = "25334--25349",
ISBN = "979-8-89176-256-5",
abstract = "Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and weaken generalization to states not covered by the expert data. Additionally, critical steps{---}such as planning, complex reasoning for intermediate subtasks, and strategic decision-making{---}are essential to success in agent tasks, so learning these steps is the key to improving LLM agents. For more effective and efficient agent tuning, we propose ATLAS that identifies the critical steps in expert trajectories and finetunes LLMs solely on these steps with reduced costs. By steering the training{'}s focus to a few critical steps, our method mitigates the risk of overfitting entire trajectories and promotes generalization across different environments and tasks. In extensive experiments, an LLM finetuned on only 30{\%} critical steps selected by ATLAS outperforms the LLM finetuned on all steps and recent open-source LLM agents. ATLAS maintains and improves base LLM skills as generalist agents interacting with diverse environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-atlas">
<titleInfo>
<title>ATLAS: Agent Tuning via Learning Critical Steps</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhixun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yali</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Zhou</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and weaken generalization to states not covered by the expert data. Additionally, critical steps—such as planning, complex reasoning for intermediate subtasks, and strategic decision-making—are essential to success in agent tasks, so learning these steps is the key to improving LLM agents. For more effective and efficient agent tuning, we propose ATLAS that identifies the critical steps in expert trajectories and finetunes LLMs solely on these steps with reduced costs. By steering the training’s focus to a few critical steps, our method mitigates the risk of overfitting entire trajectories and promotes generalization across different environments and tasks. In extensive experiments, an LLM finetuned on only 30% critical steps selected by ATLAS outperforms the LLM finetuned on all steps and recent open-source LLM agents. ATLAS maintains and improves base LLM skills as generalist agents interacting with diverse environments.</abstract>
<identifier type="citekey">chen-etal-2025-atlas</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1299</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1299/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>25334</start>
<end>25349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ATLAS: Agent Tuning via Learning Critical Steps
%A Chen, Zhixun
%A Li, Ming
%A Huang, Yuxuan
%A Du, Yali
%A Fang, Meng
%A Zhou, Tianyi
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F chen-etal-2025-atlas
%X Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and weaken generalization to states not covered by the expert data. Additionally, critical steps—such as planning, complex reasoning for intermediate subtasks, and strategic decision-making—are essential to success in agent tasks, so learning these steps is the key to improving LLM agents. For more effective and efficient agent tuning, we propose ATLAS that identifies the critical steps in expert trajectories and finetunes LLMs solely on these steps with reduced costs. By steering the training’s focus to a few critical steps, our method mitigates the risk of overfitting entire trajectories and promotes generalization across different environments and tasks. In extensive experiments, an LLM finetuned on only 30% critical steps selected by ATLAS outperforms the LLM finetuned on all steps and recent open-source LLM agents. ATLAS maintains and improves base LLM skills as generalist agents interacting with diverse environments.
%R 10.18653/v1/2025.findings-acl.1299
%U https://aclanthology.org/2025.findings-acl.1299/
%U https://doi.org/10.18653/v1/2025.findings-acl.1299
%P 25334-25349
Markdown (Informal)
[ATLAS: Agent Tuning via Learning Critical Steps](https://aclanthology.org/2025.findings-acl.1299/) (Chen et al., Findings 2025)
ACL
- Zhixun Chen, Ming Li, Yuxuan Huang, Yali Du, Meng Fang, and Tianyi Zhou. 2025. ATLAS: Agent Tuning via Learning Critical Steps. In Findings of the Association for Computational Linguistics: ACL 2025, pages 25334–25349, Vienna, Austria. Association for Computational Linguistics.