TutorMoments: Do AI tutors know when to help and when to hold back?
Effective tutoring requires judgment about student readiness, raising questions about whether AI can develop the nuance human educators use daily.
Get smart on it
TutorMoments is a framework that measures whether language models can make good decisions about when to help students and when to push them to do harder thinking during math tutoring sessions. The framework is built on real tutoring transcripts where experienced teachers marked key moments where tutors had to choose between making problems easier or encouraging deeper reasoning. When given only a basic instruction to "tutor well," language models tend to over-help by giving too much support, though explicitly spelling out the trade-off in the prompt improves their performance. The research matters because most existing benchmarks for AI tutors reward single fixed behaviors without considering whether that behavior was right for what the student actually needed at that moment, but good tutoring requires making judgment calls based on each student's current understanding.
Related news
Meet Shepherd: An Open-Source Python Substrate That Lets Meta-Agents Fork, Replay, and Revert Any Agent Run
Long-running agents accumulate state that no transcript captures. A coding agent at step 10 holds edited files, a running dev server, installed packages, and a warm prompt cache. When it misreads a traceback and rewrites a file that was already correct, neither available recovery path is cheap: patching forward grows the context and the token bill, and restarting from step one re-pays every model and tool call while reproducing nothing exactly, because runs are non-deterministic. Jumping back t
How to Disable Gemini in Gmail and Google Docs
New AI toolbars and prompts are showing up in Google Docs and Gmail. If you don’t want Gemini’s help in writing documents and emails, here’s how to turn that stuff off.
