@inproceedings{zhang-etal-2026-individual,
title = "From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams",
author = "Zhang, Tong and
Wu, Yang and
Shi, Yufei and
Yao, Rujing and
Jiang, Zhuoren and
Liu, Xiaozhong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1920/",
pages = "38552--38565",
ISBN = "979-8-89176-395-1",
abstract = "In heterogeneous scientific teams, proactive team agents can serve as effective assistants regarding the research progress of the project. However, proactive agents always suffer from collaborative myopia: a greedy optimization for immediate task accuracy which ignore the long-term goal of team sustainability. This leads to the Individual-centric Trap, where capable experts (e.g., PIs) are disproportionately overloaded while Junior roles remain underutilized. Therefore, neglecting opportunity costs in task allocation can implicitly erodes the enduring performance of the team. To solve this imbalance between efficiency and sustainability, we propose GT-PMARL (Game-Theoretic Proactive Multi-Agent Reinforcement Learning). By internalizing the opportunity cost as a key consideration in individual decision-making, the collaboration logic of agents has been reshaped. Our framework employs: (1) a Positive-Unlabeled scorer to anchor intervention quality under sparse supervision; (2) a Nash-Pareto competitive objective to seek an equilibrium between individual task excellence and collective load balancing. Empirical experiments in scientific workflows show that GT-PMARL effectively maintains high performance while preventing experts from over-developing. Our work provides a scalable paradigm for building a sustainable and balanced human-AI collaborative ecosystem."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-individual">
<titleInfo>
<title>From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rujing</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuoren</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaozhong</namePart>
<namePart type="family">Liu</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>In heterogeneous scientific teams, proactive team agents can serve as effective assistants regarding the research progress of the project. However, proactive agents always suffer from collaborative myopia: a greedy optimization for immediate task accuracy which ignore the long-term goal of team sustainability. This leads to the Individual-centric Trap, where capable experts (e.g., PIs) are disproportionately overloaded while Junior roles remain underutilized. Therefore, neglecting opportunity costs in task allocation can implicitly erodes the enduring performance of the team. To solve this imbalance between efficiency and sustainability, we propose GT-PMARL (Game-Theoretic Proactive Multi-Agent Reinforcement Learning). By internalizing the opportunity cost as a key consideration in individual decision-making, the collaboration logic of agents has been reshaped. Our framework employs: (1) a Positive-Unlabeled scorer to anchor intervention quality under sparse supervision; (2) a Nash-Pareto competitive objective to seek an equilibrium between individual task excellence and collective load balancing. Empirical experiments in scientific workflows show that GT-PMARL effectively maintains high performance while preventing experts from over-developing. Our work provides a scalable paradigm for building a sustainable and balanced human-AI collaborative ecosystem.</abstract>
<identifier type="citekey">zhang-etal-2026-individual</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1920/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>38552</start>
<end>38565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams
%A Zhang, Tong
%A Wu, Yang
%A Shi, Yufei
%A Yao, Rujing
%A Jiang, Zhuoren
%A Liu, Xiaozhong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F zhang-etal-2026-individual
%X In heterogeneous scientific teams, proactive team agents can serve as effective assistants regarding the research progress of the project. However, proactive agents always suffer from collaborative myopia: a greedy optimization for immediate task accuracy which ignore the long-term goal of team sustainability. This leads to the Individual-centric Trap, where capable experts (e.g., PIs) are disproportionately overloaded while Junior roles remain underutilized. Therefore, neglecting opportunity costs in task allocation can implicitly erodes the enduring performance of the team. To solve this imbalance between efficiency and sustainability, we propose GT-PMARL (Game-Theoretic Proactive Multi-Agent Reinforcement Learning). By internalizing the opportunity cost as a key consideration in individual decision-making, the collaboration logic of agents has been reshaped. Our framework employs: (1) a Positive-Unlabeled scorer to anchor intervention quality under sparse supervision; (2) a Nash-Pareto competitive objective to seek an equilibrium between individual task excellence and collective load balancing. Empirical experiments in scientific workflows show that GT-PMARL effectively maintains high performance while preventing experts from over-developing. Our work provides a scalable paradigm for building a sustainable and balanced human-AI collaborative ecosystem.
%U https://aclanthology.org/2026.findings-acl.1920/
%P 38552-38565
Markdown (Informal)
[From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams](https://aclanthology.org/2026.findings-acl.1920/) (Zhang et al., Findings 2026)
ACL