Hybrid-Gym

Popular repositories Loading

1. Hybrid-Gym Hybrid-Gym Public

   Code for "Hybrid-Gym: Training Coding Agents to Generalize Across Tasks" (ICML 2026)

   Python 10 4

2. Hybrid-Gym.github.io Hybrid-Gym.github.io Public

   JavaScript

3. critic-rubrics critic-rubrics Public

   Forked from OpenHands/critic-rubrics

   Official repo for paper "A Rubric-Supervised Critic from Sparse Real-World Outcomes". Type-safe function-calling-based LLM-as-judge evaluation framework for agent behavior prediction and analysis.

   Python

4. benchmarks benchmarks Public

   Forked from OpenHands/benchmarks

   Evaluation harness for OpenHands V1.

   Python