DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
This addresses a specific bottleneck in AI reasoning for tasks requiring dynamic logical inference, though it is incremental as it builds on existing methods without architectural changes.
The paper tackles the challenge of Theory-of-Mind reasoning in large language models by proposing DEL-ToM, a framework that uses inference-time scaling with Dynamic Epistemic Logic to improve verifiable reasoning, resulting in consistent performance gains across model scales and benchmarks.
Theory-of-Mind (ToM) tasks pose a unique challenge for large language models (LLMs), which often lack the capability for dynamic logical reasoning. In this work, we propose DEL-ToM, a framework that improves verifiable ToM reasoning through inference-time scaling rather than architectural changes. Our approach decomposes ToM tasks into a sequence of belief updates grounded in Dynamic Epistemic Logic (DEL), enabling structured and verifiable dynamic logical reasoning. We use data generated automatically via a DEL simulator to train a verifier, which we call the Process Belief Model (PBM), to score each belief update step. During inference, the PBM evaluates candidate belief traces from the LLM and selects the highest-scoring one. This allows LLMs to allocate extra inference-time compute to yield more transparent reasoning. Experiments across model scales and benchmarks show that DEL-ToM consistently improves performance, demonstrating that verifiable belief supervision significantly enhances LLMs' ToM capabilities without retraining. Code is available at https://github.com/joel-wu/DEL-ToM.