@inproceedings{cheng-etal-2026-apeiron,
title = "Apeiron: A Scalable {LLM}-agentic Framework for Autonomous Full-lifecycle Demand-optimized Application Synthesis",
author = "Cheng, Junyan and
Srivastava, Ankit and
Zeng, Jessie and
Drinic, Milenko and
Stokes, Jack W.",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.188/",
pages = "3868--3899",
ISBN = "979-8-89176-395-1",
abstract = "We introduce Apeiron, a scalable and extensible framework for addressing *amorphous* user demands through autonomous, full-lifecycle application synthesis. Apeiron models the unstructured app development process as a heuristic optimization problem combining (i) a Computer-Use Agent (CUA) evaluator that simulates personas and demands, (ii) an *Activity Tracer* that grounds feedback in code-level interaction traces, and (iii) a *Locality Controller* that constrains changes during continuous integration and delivery (CI/CD). Furthermore, we introduce an innovative data generation approach using CUA-as-a-Judge to tackle data scarcity. Across 300 app scenarios, 2,400 personas, and 46,338 demands, Apeiron outperformed baselines by 10.7{\%} in CUA ratings and 27.8{\%} in user-demand task scores. The optimization process enhances task scores by 64.7{\%}, and the tracer contributes a 25.1{\%} gain. In CI/CD, Apeiron effectively restores 96.9{\%} of the pre-shift mean CUA rating in one optimization step with {\ensuremath{<}}30{\%} code changes in response to 30{\%} demand shifts. Finally, a user study ($N=18$) shows that our CUA ratings strongly correlate with human judgment (Spearman{'}s $\rho=0.685$) and that users prefer Apeiron-synthesized apps over baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2026-apeiron">
<titleInfo>
<title>Apeiron: A Scalable LLM-agentic Framework for Autonomous Full-lifecycle Demand-optimized Application Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyan</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessie</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milenko</namePart>
<namePart type="family">Drinic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Stokes</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>We introduce Apeiron, a scalable and extensible framework for addressing *amorphous* user demands through autonomous, full-lifecycle application synthesis. Apeiron models the unstructured app development process as a heuristic optimization problem combining (i) a Computer-Use Agent (CUA) evaluator that simulates personas and demands, (ii) an *Activity Tracer* that grounds feedback in code-level interaction traces, and (iii) a *Locality Controller* that constrains changes during continuous integration and delivery (CI/CD). Furthermore, we introduce an innovative data generation approach using CUA-as-a-Judge to tackle data scarcity. Across 300 app scenarios, 2,400 personas, and 46,338 demands, Apeiron outperformed baselines by 10.7% in CUA ratings and 27.8% in user-demand task scores. The optimization process enhances task scores by 64.7%, and the tracer contributes a 25.1% gain. In CI/CD, Apeiron effectively restores 96.9% of the pre-shift mean CUA rating in one optimization step with \ensuremath<30% code changes in response to 30% demand shifts. Finally, a user study (N=18) shows that our CUA ratings strongly correlate with human judgment (Spearman’s ρ=0.685) and that users prefer Apeiron-synthesized apps over baselines.</abstract>
<identifier type="citekey">cheng-etal-2026-apeiron</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.188/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3868</start>
<end>3899</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Apeiron: A Scalable LLM-agentic Framework for Autonomous Full-lifecycle Demand-optimized Application Synthesis
%A Cheng, Junyan
%A Srivastava, Ankit
%A Zeng, Jessie
%A Drinic, Milenko
%A Stokes, Jack W.
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F cheng-etal-2026-apeiron
%X We introduce Apeiron, a scalable and extensible framework for addressing *amorphous* user demands through autonomous, full-lifecycle application synthesis. Apeiron models the unstructured app development process as a heuristic optimization problem combining (i) a Computer-Use Agent (CUA) evaluator that simulates personas and demands, (ii) an *Activity Tracer* that grounds feedback in code-level interaction traces, and (iii) a *Locality Controller* that constrains changes during continuous integration and delivery (CI/CD). Furthermore, we introduce an innovative data generation approach using CUA-as-a-Judge to tackle data scarcity. Across 300 app scenarios, 2,400 personas, and 46,338 demands, Apeiron outperformed baselines by 10.7% in CUA ratings and 27.8% in user-demand task scores. The optimization process enhances task scores by 64.7%, and the tracer contributes a 25.1% gain. In CI/CD, Apeiron effectively restores 96.9% of the pre-shift mean CUA rating in one optimization step with \ensuremath<30% code changes in response to 30% demand shifts. Finally, a user study (N=18) shows that our CUA ratings strongly correlate with human judgment (Spearman’s ρ=0.685) and that users prefer Apeiron-synthesized apps over baselines.
%U https://aclanthology.org/2026.findings-acl.188/
%P 3868-3899
Markdown (Informal)
[Apeiron: A Scalable LLM-agentic Framework for Autonomous Full-lifecycle Demand-optimized Application Synthesis](https://aclanthology.org/2026.findings-acl.188/) (Cheng et al., Findings 2026)
ACL