METIS: Mentoring Engine for Thoughtful Inquiry & Solutions
This addresses the need for accessible research mentorship for students, though it appears incremental as it builds on existing AI tools with stage-aware enhancements.
The authors tackled the problem of students lacking expert research mentorship by developing METIS, an AI mentor that assists undergraduates from idea to paper, achieving LLM judge preference over Claude Sonnet 4.5 in 71% and GPT-5 in 54% of cases on single-turn prompts.
Many students lack access to expert research mentorship. We ask whether an AI mentor can move undergraduates from an idea to a paper. We build METIS, a tool-augmented, stage-aware assistant with literature search, curated guidelines, methodology checks, and memory. We evaluate METIS against GPT-5 and Claude Sonnet 4.5 across six writing stages using LLM-as-a-judge pairwise preferences, student-persona rubrics, short multi-turn tutoring, and evidence/compliance checks. On 90 single-turn prompts, LLM judges preferred METIS to Claude Sonnet 4.5 in 71% and to GPT-5 in 54%. Student scores (clarity/actionability/constraint-fit; 90 prompts x 3 judges) are higher across stages. In multi-turn sessions (five scenarios/agent), METIS yields slightly higher final quality than GPT-5. Gains concentrate in document-grounded stages (D-F), consistent with stage-aware routing and groundings failure modes include premature tool routing, shallow grounding, and occasional stage misclassification.