@inproceedings{liu-etal-2024-pract,
title = "{PRACT}: Optimizing Principled Reasoning and Acting of {LLM} Agent",
author = "Liu, Zhiwei and
Yao, Weiran and
Zhang, Jianguo and
Liu, Zuxin and
Yang, Liangwei and
R N, Rithesh and
Lan, Tian and
Zhu, Ming and
Tan, Juntao and
Kokane, Shirley and
Hoang, Thai Quoc and
Niebles, Juan Carlos and
Heinecke, Shelby and
Wang, Huan and
Savarese, Silvio and
Xiong, Caiming",
editor = "Barak, Libby and
Alikhani, Malihe",
booktitle = "Proceedings of the 28th Conference on Computational Natural Language Learning",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.conll-1.33",
pages = "442--446",
abstract = "We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the use of text gradients from a reflection and optimization engine to derive these action principles. To adapt action principles to specific task requirements, we propose a new optimization framework, Reflective Principle Optimization (RPO). After execution, RPO employs a reflector to critique current action principles and an optimizer to update them accordingly.We investigate the RPO framework under two scenarios: Reward-RPO, which uses environmental rewards for reflection, and Self-RPO, which conducts self-reflection without external rewards. Additionally, we developed two RPO methods, RPO-Traj and RPO-Batch, to adapt to different settings.Experimental results across four environments demonstrate that the PRAct agent, leveraging the RPO framework, can effectively learn and apply action principles to enhance performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-pract">
<titleInfo>
<title>PRACT: Optimizing Principled Reasoning and Acting of LLM Agent</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiran</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianguo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuxin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangwei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rithesh</namePart>
<namePart type="family">R N</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirley</namePart>
<namePart type="family">Kokane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thai</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Carlos</namePart>
<namePart type="family">Niebles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shelby</namePart>
<namePart type="family">Heinecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvio</namePart>
<namePart type="family">Savarese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the use of text gradients from a reflection and optimization engine to derive these action principles. To adapt action principles to specific task requirements, we propose a new optimization framework, Reflective Principle Optimization (RPO). After execution, RPO employs a reflector to critique current action principles and an optimizer to update them accordingly.We investigate the RPO framework under two scenarios: Reward-RPO, which uses environmental rewards for reflection, and Self-RPO, which conducts self-reflection without external rewards. Additionally, we developed two RPO methods, RPO-Traj and RPO-Batch, to adapt to different settings.Experimental results across four environments demonstrate that the PRAct agent, leveraging the RPO framework, can effectively learn and apply action principles to enhance performance.</abstract>
<identifier type="citekey">liu-etal-2024-pract</identifier>
<location>
<url>https://aclanthology.org/2024.conll-1.33</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>442</start>
<end>446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PRACT: Optimizing Principled Reasoning and Acting of LLM Agent
%A Liu, Zhiwei
%A Yao, Weiran
%A Zhang, Jianguo
%A Liu, Zuxin
%A Yang, Liangwei
%A R N, Rithesh
%A Lan, Tian
%A Zhu, Ming
%A Tan, Juntao
%A Kokane, Shirley
%A Hoang, Thai Quoc
%A Niebles, Juan Carlos
%A Heinecke, Shelby
%A Wang, Huan
%A Savarese, Silvio
%A Xiong, Caiming
%Y Barak, Libby
%Y Alikhani, Malihe
%S Proceedings of the 28th Conference on Computational Natural Language Learning
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F liu-etal-2024-pract
%X We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the use of text gradients from a reflection and optimization engine to derive these action principles. To adapt action principles to specific task requirements, we propose a new optimization framework, Reflective Principle Optimization (RPO). After execution, RPO employs a reflector to critique current action principles and an optimizer to update them accordingly.We investigate the RPO framework under two scenarios: Reward-RPO, which uses environmental rewards for reflection, and Self-RPO, which conducts self-reflection without external rewards. Additionally, we developed two RPO methods, RPO-Traj and RPO-Batch, to adapt to different settings.Experimental results across four environments demonstrate that the PRAct agent, leveraging the RPO framework, can effectively learn and apply action principles to enhance performance.
%U https://aclanthology.org/2024.conll-1.33
%P 442-446
Markdown (Informal)
[PRACT: Optimizing Principled Reasoning and Acting of LLM Agent](https://aclanthology.org/2024.conll-1.33) (Liu et al., CoNLL 2024)
ACL
- Zhiwei Liu, Weiran Yao, Jianguo Zhang, Zuxin Liu, Liangwei Yang, Rithesh R N, Tian Lan, Ming Zhu, Juntao Tan, Shirley Kokane, Thai Quoc Hoang, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, and Caiming Xiong. 2024. PRACT: Optimizing Principled Reasoning and Acting of LLM Agent. In Proceedings of the 28th Conference on Computational Natural Language Learning, pages 442–446, Miami, FL, USA. Association for Computational Linguistics.