@inproceedings{le-etal-2026-specmind,
title = "{S}pec{M}ind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference",
author = "Le, Cuong Chi and
Pham, Minh V.t. and
Vu, Tung D. and
Cuong, Van Duc and
Huy, Phan Nhat and
Hoang, Phan Nhat and
Nguyen, Tien N.",
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.1687/",
doi = "10.18653/v1/2026.acl-long.1687",
pages = "36409--36424",
ISBN = "979-8-89176-390-6",
abstract = "Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large language model (LLM)-based methods have shown successes in generating specifications such as postconditions, but existing single-pass prompting often yields inaccurate results. In this paper, we present SpecMind, a novel framework for postcondition generation that treats LLMs as interactive and exploratory reasoners rather than one-shot generators. SpecMind employs feedback-driven multi-turn prompting approaches, enabling the model to iteratively refine candidate postconditions by incorporating implicit and explicit correctness feedback, while autonomously deciding when to stop. This process fosters deeper code comprehension and improves alignment with true program behavior via exploratory attempts. Our empirical evaluation shows that SpecMind significantly outperforms state-of-the-art approaches in both accuracy and completeness of generated postconditions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-etal-2026-specmind">
<titleInfo>
<title>SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cuong</namePart>
<namePart type="given">Chi</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">V.t.</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tung</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Van</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Cuong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phan</namePart>
<namePart type="given">Nhat</namePart>
<namePart type="family">Huy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phan</namePart>
<namePart type="given">Nhat</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tien</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Nguyen</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>Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large language model (LLM)-based methods have shown successes in generating specifications such as postconditions, but existing single-pass prompting often yields inaccurate results. In this paper, we present SpecMind, a novel framework for postcondition generation that treats LLMs as interactive and exploratory reasoners rather than one-shot generators. SpecMind employs feedback-driven multi-turn prompting approaches, enabling the model to iteratively refine candidate postconditions by incorporating implicit and explicit correctness feedback, while autonomously deciding when to stop. This process fosters deeper code comprehension and improves alignment with true program behavior via exploratory attempts. Our empirical evaluation shows that SpecMind significantly outperforms state-of-the-art approaches in both accuracy and completeness of generated postconditions.</abstract>
<identifier type="citekey">le-etal-2026-specmind</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.1687</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1687/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>36409</start>
<end>36424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference
%A Le, Cuong Chi
%A Pham, Minh V.t.
%A Vu, Tung D.
%A Cuong, Van Duc
%A Huy, Phan Nhat
%A Hoang, Phan Nhat
%A Nguyen, Tien N.
%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 le-etal-2026-specmind
%X Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large language model (LLM)-based methods have shown successes in generating specifications such as postconditions, but existing single-pass prompting often yields inaccurate results. In this paper, we present SpecMind, a novel framework for postcondition generation that treats LLMs as interactive and exploratory reasoners rather than one-shot generators. SpecMind employs feedback-driven multi-turn prompting approaches, enabling the model to iteratively refine candidate postconditions by incorporating implicit and explicit correctness feedback, while autonomously deciding when to stop. This process fosters deeper code comprehension and improves alignment with true program behavior via exploratory attempts. Our empirical evaluation shows that SpecMind significantly outperforms state-of-the-art approaches in both accuracy and completeness of generated postconditions.
%R 10.18653/v1/2026.acl-long.1687
%U https://aclanthology.org/2026.acl-long.1687/
%U https://doi.org/10.18653/v1/2026.acl-long.1687
%P 36409-36424
Markdown (Informal)
[SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference](https://aclanthology.org/2026.acl-long.1687/) (Le et al., ACL 2026)
ACL
- Cuong Chi Le, Minh V.t. Pham, Tung D. Vu, Van Duc Cuong, Phan Nhat Huy, Phan Nhat Hoang, and Tien N. Nguyen. 2026. SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36409–36424, San Diego, California, United States. Association for Computational Linguistics.