2606.11724v1 Jun 10, 2026 cs.AI

Mind the Perspective: Let's Reason Recursively for Theory of Mind

Mengjie Yang
Mengjie Yang
Citations: 2
h-index: 1
N. Lipovetzky
N. Lipovetzky
Citations: 1,644
h-index: 20
Yanbei Jiang
Yanbei Jiang
Citations: 44
h-index: 4
Chao Lei
Chao Lei
Citations: 39
h-index: 3
Guang Hu
Guang Hu
The University of Melbourne
Citations: 24
h-index: 3

Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Existing prompting-based approaches improve ToM reasoning through observable-event filtering or temporal belief chains, without explicitly modeling nested beliefs. We introduce RecToM, an inference-time framework for ToM reasoning that models nested beliefs via recursive perspective construction. RecToM constructs each character perspective from the preceding character perspective along the character chain specified by the question, reducing higher-order belief questions to actual-world questions within the final constructed perspective. We further provide a KD45 analysis showing that RecToM's perspective construction induces a well-formed belief modality beyond simple event filtering. Experiments on ToM benchmarks, including Hi-ToM, Big-ToM, and FanToM, across multiple LLM backbones show that RecToM consistently outperforms recent advanced approaches, achieving state-of-the-art performance. Notably, RecToM reaches 100\% accuracy on Hi-ToM with GPT-5.4 and Qwen3.5, a benchmark requiring higher-order ToM reasoning.

0 Citations
0 Influential
10 Altmetric
50.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!