Theory of Mind in Action: The Instruction Inference Task in Dynamic Human-Agent Collaboration
cs.CL, cs.AI, cs.MA
Submitted: 2025-06-26
Updated: 2026-04-17
Code: https://github.com/fardinsaad/Tomcat-LLM
Terminology
Sources
- LLM Theory of Mind and Alignment: Opportunities and Risks
- LLMs achieve adult human performance on higher-order theory of mind tasks
- Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain
- GPT-4o reads the mind in the eyes
- Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks
- Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task
- Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning
- ReAct: Synergizing Reasoning and Acting in Language Models
- Recursive Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data