@inproceedings{xiao-etal-2026-acies,
title = "{ACIES}: A Self-Evolving Agentic Contract-Based Framework for Cyber-Physical System Control Synthesis",
author = "Xiao, Yifeng and
Ni, Zhiyu and
Song, Dinghong and
Zhou, Mi and
Nuzzo, Pierluigi",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.36/",
pages = "541--550",
ISBN = "979-8-89176-485-9",
abstract = "Large language models (LLMs) are increasingly being explored in cyber-physical system design as a promising tool to facilitate the conversion of natural-language requirements into formal specifications, and the generation of plans and controllers that provably satisfy them. Existing LLM-based pipelines, however, mostly validate the designed controllers by simulation, and carry no mechanism for improving their outcomes from past designs. We present ACIES, a self-evolving agentic contract-based framework for cyber-physical system control synthesis. Given a set of system requirements, ACIES automatically generates a control architecture that realizes the requirements using a sequence of synthesis episodes. Within each episode, a Translator agent formalizes the system requirements into temporal logic, and a Decomposer agent structures them into a system-level contract and proposes a decomposition into component-level contracts that can be independently implemented. A formal verification step is then integrated in the decomposition loop to check whether the component-level contracts are consistent, compatible, and provide a correct refinement of the system-level contract. Each failed check, at the verification or implementation step, returns a diagnostic signal that drives automated contract repair at the system or the component level. Across episodes, a Summarizer agent distills verification outcomes into reusable lessons stored in a memory. Evaluation results on five control synthesis tasks with eight LLM backbones show that the formalized system requirements are successfully decomposed and mapped to a synthesizable control architecture that realizes them, while self-evolution reduces the Decomposer token consumption by up to 65{\%} and the end-to-end synthesis latency by up to 62{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2026-acies">
<titleInfo>
<title>ACIES: A Self-Evolving Agentic Contract-Based Framework for Cyber-Physical System Control Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifeng</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyu</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinghong</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierluigi</namePart>
<namePart type="family">Nuzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly being explored in cyber-physical system design as a promising tool to facilitate the conversion of natural-language requirements into formal specifications, and the generation of plans and controllers that provably satisfy them. Existing LLM-based pipelines, however, mostly validate the designed controllers by simulation, and carry no mechanism for improving their outcomes from past designs. We present ACIES, a self-evolving agentic contract-based framework for cyber-physical system control synthesis. Given a set of system requirements, ACIES automatically generates a control architecture that realizes the requirements using a sequence of synthesis episodes. Within each episode, a Translator agent formalizes the system requirements into temporal logic, and a Decomposer agent structures them into a system-level contract and proposes a decomposition into component-level contracts that can be independently implemented. A formal verification step is then integrated in the decomposition loop to check whether the component-level contracts are consistent, compatible, and provide a correct refinement of the system-level contract. Each failed check, at the verification or implementation step, returns a diagnostic signal that drives automated contract repair at the system or the component level. Across episodes, a Summarizer agent distills verification outcomes into reusable lessons stored in a memory. Evaluation results on five control synthesis tasks with eight LLM backbones show that the formalized system requirements are successfully decomposed and mapped to a synthesizable control architecture that realizes them, while self-evolution reduces the Decomposer token consumption by up to 65% and the end-to-end synthesis latency by up to 62%.</abstract>
<identifier type="citekey">xiao-etal-2026-acies</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.36/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>541</start>
<end>550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ACIES: A Self-Evolving Agentic Contract-Based Framework for Cyber-Physical System Control Synthesis
%A Xiao, Yifeng
%A Ni, Zhiyu
%A Song, Dinghong
%A Zhou, Mi
%A Nuzzo, Pierluigi
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F xiao-etal-2026-acies
%X Large language models (LLMs) are increasingly being explored in cyber-physical system design as a promising tool to facilitate the conversion of natural-language requirements into formal specifications, and the generation of plans and controllers that provably satisfy them. Existing LLM-based pipelines, however, mostly validate the designed controllers by simulation, and carry no mechanism for improving their outcomes from past designs. We present ACIES, a self-evolving agentic contract-based framework for cyber-physical system control synthesis. Given a set of system requirements, ACIES automatically generates a control architecture that realizes the requirements using a sequence of synthesis episodes. Within each episode, a Translator agent formalizes the system requirements into temporal logic, and a Decomposer agent structures them into a system-level contract and proposes a decomposition into component-level contracts that can be independently implemented. A formal verification step is then integrated in the decomposition loop to check whether the component-level contracts are consistent, compatible, and provide a correct refinement of the system-level contract. Each failed check, at the verification or implementation step, returns a diagnostic signal that drives automated contract repair at the system or the component level. Across episodes, a Summarizer agent distills verification outcomes into reusable lessons stored in a memory. Evaluation results on five control synthesis tasks with eight LLM backbones show that the formalized system requirements are successfully decomposed and mapped to a synthesizable control architecture that realizes them, while self-evolution reduces the Decomposer token consumption by up to 65% and the end-to-end synthesis latency by up to 62%.
%U https://aclanthology.org/2026.realm-1.36/
%P 541-550
Markdown (Informal)
[ACIES: A Self-Evolving Agentic Contract-Based Framework for Cyber-Physical System Control Synthesis](https://aclanthology.org/2026.realm-1.36/) (Xiao et al., REALM 2026)
ACL