OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind

Computer Science > Artificial Intelligence [Submitted on 19 May 2026] OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind Sharmin Sultana Srishty, Kazi Mahathir Rahman, Malaika Parizat Sakkhi, Samia Shahid Prianna, Shaikhul Islam Sinat 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 Focus to learn more Submission history From: Kazi Mahathir Rahman [view email] [v1] Tue, 19 May 2026 19:19:26 UTC (3,465 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)