@inproceedings{tong-etal-2026-towards,
title = "Towards Smart Exploration: Reinforcement Learning for {LLM} Agents Guided by Meta-Actions",
author = "Tong, Hanwen and
Zhang, Zhengqi and
Lu, Ruixuan and
Dai, Jincheng and
Yang, Bin and
Zheng, Bo and
Wei, Feng",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.223/",
pages = "4369--4388",
ISBN = "979-8-89176-444-6",
abstract = "Reinforcement Learning (RL) has empowered Large Language Model (LLM) agents to tackle long-horizon tasks through multi-step interactions with the environment. However, current LLM agents still rely on inefficient trial-and-error exploration, leading to frequent task failures and redundant actions. In this paper, we propose MetaAct, an RL framework that incorporates a set of high-level meta-actions to explicitly guide the agent towards promising trajectories and facilitate goal-aware exploration. Specifically, the agent is required to predict one of four meta-actions (FOCUS, GUESS, RESUME, UNDO) to constrain the direction of its subsequent actions to minimize unproductive trials. More importantly, we employ group-based RL with episode-level and step-level advantages to fine-tune the agent, enabling it to identify strategic directions more accurately and generate effective task-specific actions. Experimental results demonstrate that our method consistently outperforms the state-of-the-art approaches on ALFWorld and WebShop, achieving higher success rates with fewer steps. Our code and data are publicly available at https://github.com/HavenTong/MetaAct."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tong-etal-2026-towards">
<titleInfo>
<title>Towards Smart Exploration: Reinforcement Learning for LLM Agents Guided by Meta-Actions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanwen</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruixuan</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jincheng</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Reinforcement Learning (RL) has empowered Large Language Model (LLM) agents to tackle long-horizon tasks through multi-step interactions with the environment. However, current LLM agents still rely on inefficient trial-and-error exploration, leading to frequent task failures and redundant actions. In this paper, we propose MetaAct, an RL framework that incorporates a set of high-level meta-actions to explicitly guide the agent towards promising trajectories and facilitate goal-aware exploration. Specifically, the agent is required to predict one of four meta-actions (FOCUS, GUESS, RESUME, UNDO) to constrain the direction of its subsequent actions to minimize unproductive trials. More importantly, we employ group-based RL with episode-level and step-level advantages to fine-tune the agent, enabling it to identify strategic directions more accurately and generate effective task-specific actions. Experimental results demonstrate that our method consistently outperforms the state-of-the-art approaches on ALFWorld and WebShop, achieving higher success rates with fewer steps. Our code and data are publicly available at https://github.com/HavenTong/MetaAct.</abstract>
<identifier type="citekey">tong-etal-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.223/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4369</start>
<end>4388</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Smart Exploration: Reinforcement Learning for LLM Agents Guided by Meta-Actions
%A Tong, Hanwen
%A Zhang, Zhengqi
%A Lu, Ruixuan
%A Dai, Jincheng
%A Yang, Bin
%A Zheng, Bo
%A Wei, Feng
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F tong-etal-2026-towards
%X Reinforcement Learning (RL) has empowered Large Language Model (LLM) agents to tackle long-horizon tasks through multi-step interactions with the environment. However, current LLM agents still rely on inefficient trial-and-error exploration, leading to frequent task failures and redundant actions. In this paper, we propose MetaAct, an RL framework that incorporates a set of high-level meta-actions to explicitly guide the agent towards promising trajectories and facilitate goal-aware exploration. Specifically, the agent is required to predict one of four meta-actions (FOCUS, GUESS, RESUME, UNDO) to constrain the direction of its subsequent actions to minimize unproductive trials. More importantly, we employ group-based RL with episode-level and step-level advantages to fine-tune the agent, enabling it to identify strategic directions more accurately and generate effective task-specific actions. Experimental results demonstrate that our method consistently outperforms the state-of-the-art approaches on ALFWorld and WebShop, achieving higher success rates with fewer steps. Our code and data are publicly available at https://github.com/HavenTong/MetaAct.
%U https://aclanthology.org/2026.findings-aacl.223/
%P 4369-4388
Markdown (Informal)
[Towards Smart Exploration: Reinforcement Learning for LLM Agents Guided by Meta-Actions](https://aclanthology.org/2026.findings-aacl.223/) (Tong et al., Findings 2026)
ACL