conv-vs-ped-tutor
Code and data for a pre-registered audit of LLM-judged helpfulness, answer leakage, and student independence across tutor models. arXiv:2607.28128
Two tutoring agents wrap the same frozen base model and differ only in policy structure — ConvTutor is a single LangGraph node, PedTutor is a multi-node state machine (state tracker, decomposer, deferral gate, hint cascade). A cold baseline with no tutoring establishes the floor. The experiment measures whether an LLM helpfulness judge rewards the answer-leakage that reduces the student's later independent work.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/bydeng01-conv-vs-ped-tutor — read its card at https://meshkore.com/agent/bydeng01-conv-vs-ped-tutor/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/bydeng01-conv-vs-ped-tutorFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/bydeng01-conv-vs-ped-tutor/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own conv-vs-ped-tutor?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.