RESEARCH

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

ArXiv cs.AI · Fri, 22 May 2026 04:00:00 GMT

arXiv:2605.20423v1 Announce Type: new 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 belie

Read original source Discuss with A.S.I.S