Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning

Collaborating in real-life situations rarely follows predefined roles or plans, but is established on the fly and flexibly coordinated by the interacting agents. We introduce the notion of fluid collaboration (FC), marked by frequent changes of the tasks partners assume or the resources they consume...

Full description

Saved in:
Bibliographic Details
Main Authors: Florian Schröder, Fabian Heinrich, Stefan Kopp
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Robotics and AI
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frobt.2025.1532693/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706867818758144
author Florian Schröder
Fabian Heinrich
Stefan Kopp
author_facet Florian Schröder
Fabian Heinrich
Stefan Kopp
author_sort Florian Schröder
collection DOAJ
description Collaborating in real-life situations rarely follows predefined roles or plans, but is established on the fly and flexibly coordinated by the interacting agents. We introduce the notion of fluid collaboration (FC), marked by frequent changes of the tasks partners assume or the resources they consume in response to varying requirements or affordances of the environment, tasks, or other agents. FC thus necessitates dynamic, action-oriented Theory of Mind reasoning to enable agents to continuously infer and adapt to others’ intentions and beliefs in real-time. In this paper, we discuss how FC can be enabled in human-agent collaboration. We introduce Cooperative Cuisine, an interactive environment inspired by the game Overcooked! that facilitates human-human and human-agent collaboration in dynamic settings. We report results of an empirical study on human-human collaboration in CoCu, showing how FC can be measured empirically and that humans naturally engage in dynamically established collaboration patterns with minimal explicit communication and relying on efficient mentalizing. We then present an approach to develop artificial agents that can effectively participate in FC. Specifically, we argue for a model of dynamic mentalizing under computational constraints and integrated with action planning. We present first steps in this direction by addressing resource-rational and action-driven ToM reasoning.
format Article
id doaj-art-2ee36a908314432fa2cdbec142111201
institution DOAJ
issn 2296-9144
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Robotics and AI
spelling doaj-art-2ee36a908314432fa2cdbec1421112012025-08-20T03:16:04ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442025-08-011210.3389/frobt.2025.15326931532693Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoningFlorian SchröderFabian HeinrichStefan KoppCollaborating in real-life situations rarely follows predefined roles or plans, but is established on the fly and flexibly coordinated by the interacting agents. We introduce the notion of fluid collaboration (FC), marked by frequent changes of the tasks partners assume or the resources they consume in response to varying requirements or affordances of the environment, tasks, or other agents. FC thus necessitates dynamic, action-oriented Theory of Mind reasoning to enable agents to continuously infer and adapt to others’ intentions and beliefs in real-time. In this paper, we discuss how FC can be enabled in human-agent collaboration. We introduce Cooperative Cuisine, an interactive environment inspired by the game Overcooked! that facilitates human-human and human-agent collaboration in dynamic settings. We report results of an empirical study on human-human collaboration in CoCu, showing how FC can be measured empirically and that humans naturally engage in dynamically established collaboration patterns with minimal explicit communication and relying on efficient mentalizing. We then present an approach to develop artificial agents that can effectively participate in FC. Specifically, we argue for a model of dynamic mentalizing under computational constraints and integrated with action planning. We present first steps in this direction by addressing resource-rational and action-driven ToM reasoning.https://www.frontiersin.org/articles/10.3389/frobt.2025.1532693/fullfluid collaborationtheory of minddynamic mentalizinghuman-agent collaborationaction-oriented reasoningcooperative cuisine
spellingShingle Florian Schröder
Fabian Heinrich
Stefan Kopp
Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning
Frontiers in Robotics and AI
fluid collaboration
theory of mind
dynamic mentalizing
human-agent collaboration
action-oriented reasoning
cooperative cuisine
title Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning
title_full Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning
title_fullStr Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning
title_full_unstemmed Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning
title_short Towards fluid human-agent collaboration: From dynamic collaboration patterns to models of theory of mind reasoning
title_sort towards fluid human agent collaboration from dynamic collaboration patterns to models of theory of mind reasoning
topic fluid collaboration
theory of mind
dynamic mentalizing
human-agent collaboration
action-oriented reasoning
cooperative cuisine
url https://www.frontiersin.org/articles/10.3389/frobt.2025.1532693/full
work_keys_str_mv AT florianschroder towardsfluidhumanagentcollaborationfromdynamiccollaborationpatternstomodelsoftheoryofmindreasoning
AT fabianheinrich towardsfluidhumanagentcollaborationfromdynamiccollaborationpatternstomodelsoftheoryofmindreasoning
AT stefankopp towardsfluidhumanagentcollaborationfromdynamiccollaborationpatternstomodelsoftheoryofmindreasoning