OpenEnv Hackathon India 2026

AxiomForgeAI

A self-improving math RL environment. The model practices on verified problems, generates new challenges when ready, and learns from solution attempts whose reasoning steps and final answers agree.

POST /reset

Start a new episode. Returns a math question with topic and difficulty metadata.

POST /step

Submit a solution for the current question. Returns reward, feedback, and scoring breakdown.

GET /state

Get the current episode state including episode ID and step count.

GET /schema

Returns JSON schemas for action and observation types.

GET /health

Health check endpoint. Returns server status and environment availability.

WS /ws

WebSocket endpoint for persistent sessions. Supports concurrent multi-agent connections.