@inproceedings{cheng-etal-2026-proret,
title = "{P}ro{R}et-{VLA}: Bridging Prospection and Retrospection for Long-Horizon Robotic Manipulation",
author = "Cheng, Enhua and
Fang, Xiaoyuan and
Wang, Yuxuan and
Li, Piji",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.620/",
pages = "13029--13047",
ISBN = "979-8-89176-462-0",
abstract = "Vision-Language-Action (VLA) models map visual observations and language instructions to low-level control actions, but their reliance on the current observation often limits temporal continuity in long-horizon manipulation. We propose ProRet-VLA, a temporal reasoning framework that links prospection and retrospection through predictive consistency. ProRet-VLA maintains compact episodic memories and predicts future observations from temporally enriched context. Rather than using future prediction only as an auxiliary target, we use its prediction error as a self-supervised deviation signal to train a lightweight Deviation Predictor. During inference, the predicted deviation conditions token-wise fusion between current context and retrieved memory, allowing memory usage to vary across decision stages without accessing future observations. Experiments on CALVIN ABC-D and LIBERO show that ProRet-VLA improves long-horizon task completion, achieving an average length of 4.50 on CALVIN and a 96.7{\%} average success rate on LIBERO. Real-world experiments on two long-horizon manipulation tasks further indicate improved temporal progress tracking over strong VLA baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2026-proret">
<titleInfo>
<title>ProRet-VLA: Bridging Prospection and Retrospection for Long-Horizon Robotic Manipulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enhua</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyuan</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piji</namePart>
<namePart type="family">Li</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Vision-Language-Action (VLA) models map visual observations and language instructions to low-level control actions, but their reliance on the current observation often limits temporal continuity in long-horizon manipulation. We propose ProRet-VLA, a temporal reasoning framework that links prospection and retrospection through predictive consistency. ProRet-VLA maintains compact episodic memories and predicts future observations from temporally enriched context. Rather than using future prediction only as an auxiliary target, we use its prediction error as a self-supervised deviation signal to train a lightweight Deviation Predictor. During inference, the predicted deviation conditions token-wise fusion between current context and retrieved memory, allowing memory usage to vary across decision stages without accessing future observations. Experiments on CALVIN ABC-D and LIBERO show that ProRet-VLA improves long-horizon task completion, achieving an average length of 4.50 on CALVIN and a 96.7% average success rate on LIBERO. Real-world experiments on two long-horizon manipulation tasks further indicate improved temporal progress tracking over strong VLA baselines.</abstract>
<identifier type="citekey">cheng-etal-2026-proret</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.620/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>13029</start>
<end>13047</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ProRet-VLA: Bridging Prospection and Retrospection for Long-Horizon Robotic Manipulation
%A Cheng, Enhua
%A Fang, Xiaoyuan
%A Wang, Yuxuan
%A Li, Piji
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F cheng-etal-2026-proret
%X Vision-Language-Action (VLA) models map visual observations and language instructions to low-level control actions, but their reliance on the current observation often limits temporal continuity in long-horizon manipulation. We propose ProRet-VLA, a temporal reasoning framework that links prospection and retrospection through predictive consistency. ProRet-VLA maintains compact episodic memories and predicts future observations from temporally enriched context. Rather than using future prediction only as an auxiliary target, we use its prediction error as a self-supervised deviation signal to train a lightweight Deviation Predictor. During inference, the predicted deviation conditions token-wise fusion between current context and retrieved memory, allowing memory usage to vary across decision stages without accessing future observations. Experiments on CALVIN ABC-D and LIBERO show that ProRet-VLA improves long-horizon task completion, achieving an average length of 4.50 on CALVIN and a 96.7% average success rate on LIBERO. Real-world experiments on two long-horizon manipulation tasks further indicate improved temporal progress tracking over strong VLA baselines.
%U https://aclanthology.org/2026.findings-emnlp.620/
%P 13029-13047
Markdown (Informal)
[ProRet-VLA: Bridging Prospection and Retrospection for Long-Horizon Robotic Manipulation](https://aclanthology.org/2026.findings-emnlp.620/) (Cheng et al., Findings 2026)
ACL