OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind
A new approach called OSCToM uses reinforcement learning to generate adversarial examples for testing theory of mind in LLMs, achieving 76% accuracy on FANToM benchmark and 6x efficiency gain.
[2605.20423] OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind
[Submitted on 19 May 2026]
Title:OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind
View a PDF of the paper titled OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind, by Sharmin Sultana Srishty and 4 other authors
View PDF HTML (experimental)
Abstract:Large Language Models (LLMs) perform well on many language tasks, but their Theory of Mind (ToM) reasoning is still uneven in complex social settings. Existing benchmarks, including ExploreToM, do not always test the recursive beliefs and information asymmetries that make these settings difficult. This paper presents OSCToM (Observer-Self Conflict Theory of Mind), an approach for modeling nested belief conflicts in LLM-based ToM tasks. The key case is one in which an observer's view of another agent conflicts with the observer's own belief state. Such cases go beyond simple perspective-taking and require recursive, multi-layered reasoning. OSCToM combines reinforcement learning (RL), an extended domain-specific language, and compositional surrogate models to generate observer-self conflicts. In our experiments, OSCToM-8B gives the best overall result among the systems tested. It improves on the reported ExploreToM results on FANToM and remains competitive on Hi-ToM and BigToM. On the information-asymmetric FANToM benchmark, OSCToM reaches 76% accuracy, compared with the 0.2% reported by ExploreToM. The data-synthesis procedure is also 6x more efficient, indicating that targeted training data can help smaller models handle advanced cognitive reasoning. The project code is available at this https URL.
Comments: 15 pages, 12 figures containing 15 images, 3 tables. Code available at this https URL
Subjects:
Artificial Intelligence (cs.AI)
ACM classes: I.2.7; I.2.6
Cite as: arXiv:2605.20423 [cs.AI]
(or arXiv:2605.20423v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.20423
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Kazi Mahathir Rahman [view email] [v1] Tue, 19 May 2026 19:19:26 UTC (3,465 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind, by Sharmin Sultana Srishty and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)