@inproceedings{bhar-etal-2026-cocoreli,
title = "{COCORELI}: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following",
author = {Bhar, Swarnadeep and
Naim, Omar and
Metheniti, Eleni and
Cabannes, Lo{\"i}c and
Navarri, Bastien and
Kamaladdini Ezzabady, Morteza and
Asher, Nicholas},
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.36/",
pages = "516--535",
abstract = "Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actions. We identify this failure as arising from a lack of coupling between detection and execution, and propose that reliable behavior requires enforcing missing information as a precondition for action. We instantiate this principle in Cocoreli, a modular architecture that represents task structure, tracks missing information, and blocks execution until required details are resolved through targeted clarification. In Cocoreli, detection and prevention are structurally coupled: detecting a missing parameter simultaneously blocks execution. We evaluate Cocoreli in a controlled construction environment isolating underspecification and sequential execution. Cocoreli makes execution reliable by imposing explicit task structure: instructions are represented as parameterized executable objects and execution under unresolved specifications is blocked by construction, eliminating hallucinated actions. In contrast, chain-of-thought, prompt-chaining, and ReAct-style reasoning may still execute under incomplete specifications despite high detection rates. The same representation supports abstraction and reuse, and generalizes to API workflow tasks on ToolBench. These results show that reliable collaborative execution {under underspecified instructions }requires architectural enforcement, not just model capability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhar-etal-2026-cocoreli">
<titleInfo>
<title>COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swarnadeep</namePart>
<namePart type="family">Bhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Naim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleni</namePart>
<namePart type="family">Metheniti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Cabannes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bastien</namePart>
<namePart type="family">Navarri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morteza</namePart>
<namePart type="family">Kamaladdini Ezzabady</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Asher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actions. We identify this failure as arising from a lack of coupling between detection and execution, and propose that reliable behavior requires enforcing missing information as a precondition for action. We instantiate this principle in Cocoreli, a modular architecture that represents task structure, tracks missing information, and blocks execution until required details are resolved through targeted clarification. In Cocoreli, detection and prevention are structurally coupled: detecting a missing parameter simultaneously blocks execution. We evaluate Cocoreli in a controlled construction environment isolating underspecification and sequential execution. Cocoreli makes execution reliable by imposing explicit task structure: instructions are represented as parameterized executable objects and execution under unresolved specifications is blocked by construction, eliminating hallucinated actions. In contrast, chain-of-thought, prompt-chaining, and ReAct-style reasoning may still execute under incomplete specifications despite high detection rates. The same representation supports abstraction and reuse, and generalizes to API workflow tasks on ToolBench. These results show that reliable collaborative execution under underspecified instructions requires architectural enforcement, not just model capability.</abstract>
<identifier type="citekey">bhar-etal-2026-cocoreli</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.36/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>516</start>
<end>535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following
%A Bhar, Swarnadeep
%A Naim, Omar
%A Metheniti, Eleni
%A Cabannes, Loïc
%A Navarri, Bastien
%A Kamaladdini Ezzabady, Morteza
%A Asher, Nicholas
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F bhar-etal-2026-cocoreli
%X Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actions. We identify this failure as arising from a lack of coupling between detection and execution, and propose that reliable behavior requires enforcing missing information as a precondition for action. We instantiate this principle in Cocoreli, a modular architecture that represents task structure, tracks missing information, and blocks execution until required details are resolved through targeted clarification. In Cocoreli, detection and prevention are structurally coupled: detecting a missing parameter simultaneously blocks execution. We evaluate Cocoreli in a controlled construction environment isolating underspecification and sequential execution. Cocoreli makes execution reliable by imposing explicit task structure: instructions are represented as parameterized executable objects and execution under unresolved specifications is blocked by construction, eliminating hallucinated actions. In contrast, chain-of-thought, prompt-chaining, and ReAct-style reasoning may still execute under incomplete specifications despite high detection rates. The same representation supports abstraction and reuse, and generalizes to API workflow tasks on ToolBench. These results show that reliable collaborative execution under underspecified instructions requires architectural enforcement, not just model capability.
%U https://aclanthology.org/2026.sigdial-1.36/
%P 516-535
Markdown (Informal)
[COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following](https://aclanthology.org/2026.sigdial-1.36/) (Bhar et al., SIGDIAL 2026)
ACL
- Swarnadeep Bhar, Omar Naim, Eleni Metheniti, Loïc Cabannes, Bastien Navarri, Morteza Kamaladdini Ezzabady, and Nicholas Asher. 2026. COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 516–535, Atlanta, Georgia, USA. Association for Computational Linguistics.