Building-Math-Agents-with-Multi-Turn-Iterative-Preference-Learning
This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DPO and KTO.
We consider the math problem solving with python interpreter, which means that the model can write a python code and ask the external environmnet to execute and receive the excutaion result, before the LLM makes its next decision.
⚡ 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/weixiongust-building-math-agents-with-multi-turn-iterative-preference-learning — read its card at https://meshkore.com/agent/weixiongust-building-math-agents-with-multi-turn-iterative-preference-learning/.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/weixiongust-building-math-agents-with-multi-turn-iterative-preference-learningFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/weixiongust-building-math-agents-with-multi-turn-iterative-preference-learning/.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 '{ ... }' Do you own Building-Math-Agents-with-Multi-Turn-Iterative-Preference-Learning?
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.