@inproceedings{wei-etal-2026-multi,
title = "A Multi-Agent Framework for High-Interaction Terminal Simulation",
author = "Wei, Kai and
Cui, Yuwen and
Shen, Kehan and
Wei, Hua and
Wang, Guangjing",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1515/",
pages = "32828--32845",
ISBN = "979-8-89176-390-6",
abstract = "Terminal simulation, framed as a terminal command-level Turing test, is a long-standing problem of symbolic language generation in dialogue and interactive systems. Prior scripted simulators lack the flexibility needed for complex, multi-turn interactions, while LLM-based approaches often misinterpret commands, break output formats, drift from system state, and remain vulnerable to prompt injection. In this work, we propose MANTIS, a terminal simulation framework that improves realism, consistency, and robustness in command-language generation. MANTIS integrates a multi-agent architecture with a filter-based routing model that safely dispatches commands to external tools or an LLM-based agent, enabling support for interactive commands while defending against prompt injection attacks. In addition, we design an agentic file system with history pruning to preserve long-term state consistency. We release three datasets: 28,045 real terminal input-output pairs, a 1,000-session multi-turn interaction dataset, and a 25,849-instance labeled classification dataset. MANTIS outperforms state-of-the-art baselines by more than 9{\%}, achieving over 95{\%} accuracy on multi-turn terminal simulation. The dataset and source code are available at https://github.com/kaiwei666a/MANTIS{\_}Terminal{\_}Simulation"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2026-multi">
<titleInfo>
<title>A Multi-Agent Framework for High-Interaction Terminal Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuwen</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kehan</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangjing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Terminal simulation, framed as a terminal command-level Turing test, is a long-standing problem of symbolic language generation in dialogue and interactive systems. Prior scripted simulators lack the flexibility needed for complex, multi-turn interactions, while LLM-based approaches often misinterpret commands, break output formats, drift from system state, and remain vulnerable to prompt injection. In this work, we propose MANTIS, a terminal simulation framework that improves realism, consistency, and robustness in command-language generation. MANTIS integrates a multi-agent architecture with a filter-based routing model that safely dispatches commands to external tools or an LLM-based agent, enabling support for interactive commands while defending against prompt injection attacks. In addition, we design an agentic file system with history pruning to preserve long-term state consistency. We release three datasets: 28,045 real terminal input-output pairs, a 1,000-session multi-turn interaction dataset, and a 25,849-instance labeled classification dataset. MANTIS outperforms state-of-the-art baselines by more than 9%, achieving over 95% accuracy on multi-turn terminal simulation. The dataset and source code are available at https://github.com/kaiwei666a/MANTIS_Terminal_Simulation</abstract>
<identifier type="citekey">wei-etal-2026-multi</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1515/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>32828</start>
<end>32845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Agent Framework for High-Interaction Terminal Simulation
%A Wei, Kai
%A Cui, Yuwen
%A Shen, Kehan
%A Wei, Hua
%A Wang, Guangjing
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wei-etal-2026-multi
%X Terminal simulation, framed as a terminal command-level Turing test, is a long-standing problem of symbolic language generation in dialogue and interactive systems. Prior scripted simulators lack the flexibility needed for complex, multi-turn interactions, while LLM-based approaches often misinterpret commands, break output formats, drift from system state, and remain vulnerable to prompt injection. In this work, we propose MANTIS, a terminal simulation framework that improves realism, consistency, and robustness in command-language generation. MANTIS integrates a multi-agent architecture with a filter-based routing model that safely dispatches commands to external tools or an LLM-based agent, enabling support for interactive commands while defending against prompt injection attacks. In addition, we design an agentic file system with history pruning to preserve long-term state consistency. We release three datasets: 28,045 real terminal input-output pairs, a 1,000-session multi-turn interaction dataset, and a 25,849-instance labeled classification dataset. MANTIS outperforms state-of-the-art baselines by more than 9%, achieving over 95% accuracy on multi-turn terminal simulation. The dataset and source code are available at https://github.com/kaiwei666a/MANTIS_Terminal_Simulation
%U https://aclanthology.org/2026.acl-long.1515/
%P 32828-32845
Markdown (Informal)
[A Multi-Agent Framework for High-Interaction Terminal Simulation](https://aclanthology.org/2026.acl-long.1515/) (Wei et al., ACL 2026)
ACL
- Kai Wei, Yuwen Cui, Kehan Shen, Hua Wei, and Guangjing Wang. 2026. A Multi-Agent Framework for High-Interaction Terminal Simulation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 32828–32845, San Diego, California, United States. Association for Computational Linguistics.