Journal article · 2026 · Open access

Theory of mind in action: The instruction inference task in dynamic human-agent collaboration

Fardin Saad, Pradeep Kumar Murukannaiah, Munindar Paul Singh

Artificial Intelligence, 361, 104621 · Published 6 September 2026 · DOI 10.1016/j.artint.2026.104621

Open full textCite this paper

In brief

“Theory of mind in action: The instruction inference task in dynamic human-agent collaboration” is a 2026 journal article by Fardin Saad and 2 co-authors, published in Artificial Intelligence. OpenAlex counts 4 citations as of 18 November 2026, which puts it in the top 3% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Artificial Intelligence.

Citations
4
Most cited in
2026 (4)
Field-weighted impact
16.64
References
55
Authors
3

Abstract

Successful human-agent teaming relies on an agent being able to understand instructions given by a (human) principal . In many cases, an instruction may be incomplete or ambiguous. In such cases, the agent must infer the unspoken intentions from their shared context, that is, it must exercise the principal’s Theory of Mind (ToM) and infer the mental states of its principal. We consider the prospects of effective human-agent collaboration using large language models (LLMs). To assess ToM in a dynamic, goal-oriented, and collaborative environment, we introduce a novel task, Instruction Inference , in which an agent assists a principal in reaching a goal by interpreting incomplete or ambiguous instructions. We present Tomcat , an LLM-based agent, designed to exhibit ToM reasoning in interpreting and responding to the principal’s instructions. We implemented two variants of Tomcat. One, dubbed Fs-CoT (Fs for few-shot, CoT for chain-of-thought), is based on a small number of examples demonstrating the requisite structured reasoning. One, dubbed CP (commonsense prompt), relies on commonsense knowledge and information about the problem. We realized both variants of Tomcat on three leading LLMs, namely, GPT-4o, DeepSeek-R1, and Gemma-3-27B. To evaluate the effectiveness of Tomcat, we conducted a study with 52 human participants in which we provided participants with the same information as the CP variant. We computed intent accuracy, action optimality, and planning optimality to measure the ToM capabilities of Tomcat and our study participants. We found that Tomcat with Fs-CoT, particularly with GPT-4o and DeepSeek-R1, achieves performance comparable to the human participants, underscoring its ToM potential for human-agent collaboration.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Saad, F., Murukannaiah, P. K., & Singh, M. P. (2026). Theory of mind in action: The instruction inference task in dynamic human-agent collaboration. Artificial Intelligence, 361, 104621. https://doi.org/10.1016/j.artint.2026.104621

MLA 9

Saad, Fardin, et al. “Theory of mind in action: The instruction inference task in dynamic human-agent collaboration.” Artificial Intelligence, vol. 361, 2026, p. 104621. https://doi.org/10.1016/j.artint.2026.104621.

Chicago

Saad, Fardin, Pradeep Kumar Murukannaiah, and Munindar Paul Singh. 2026. “Theory of mind in action: The instruction inference task in dynamic human-agent collaboration.” Artificial Intelligence 361: 104621. https://doi.org/10.1016/j.artint.2026.104621.

Harvard

Saad, F., Murukannaiah, P. K. and Singh, M. P. (2026) ‘Theory of mind in action: The instruction inference task in dynamic human-agent collaboration’, Artificial Intelligence, 361, p. 104621. doi:10.1016/j.artint.2026.104621.

IEEE

F. Saad, P. K. Murukannaiah, and M. P. Singh, “Theory of mind in action: The instruction inference task in dynamic human-agent collaboration,” Artificial Intelligence, vol. 361, p. 104621, 2026, doi: 10.1016/j.artint.2026.104621.

BibTeX

@article{saad2026theory,
  title     = {{Theory of mind in action: The instruction inference task in dynamic human-agent collaboration}},
  author    = {Saad, Fardin and Murukannaiah, Pradeep Kumar and Singh, Munindar Paul},
  journal   = {Artificial Intelligence},
  year      = {2026},
  volume    = {361},
  pages     = {104621},
  doi       = {10.1016/j.artint.2026.104621},
  url       = {https://doi.org/10.1016/j.artint.2026.104621}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Psychology › Developmental and Educational Psychology › Child and Animal Learning Development

  • theory of mind
  • human-agent collaboration
  • large language models
  • LLM agents
  • intention inference
  • ambiguous instructions
  • chain-of-thought prompting
  • Tomcat

Work with this paper

Most-cited papers in Psychology

All highly cited Psychology papers

Questions about this paper

How do I cite this paper in APA style?

Saad, F., Murukannaiah, P. K., & Singh, M. P. (2026). Theory of mind in action: The instruction inference task in dynamic human-agent collaboration. Artificial Intelligence, 361, 104621. https://doi.org/10.1016/j.artint.2026.104621

How many times has this paper been cited?

4 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Artificial Intelligence: sign in and open the full text from this page.

Who wrote this paper?

Fardin Saad, Pradeep Kumar Murukannaiah, Munindar Paul Singh.

What is the DOI of this paper?

10.1016/j.artint.2026.104621, permanently at https://doi.org/10.1016/j.artint.2026.104621. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.