Tag
The paper proposes Collaborative Theory of Mind (CToM), a framework that trains LLMs to anticipate user responses and use those predictions to self-revise before presenting answers, improving collaborative task performance and interaction efficiency across reasoning, coding, and writing tasks.
This paper introduces Reflective Masking, a lightweight post-training method that enables mask diffusion models to perform multi-turn self-revision through token-level revision policies and history references, improving performance on reasoning tasks like Sudoku, math, code generation, and image editing.