feat: local judge server (serve_judge.py) β replaces NVIDIA NIM entirely 1d8f7f8 lebiraja Claude Sonnet 4.6 commited on Apr 25
feat(training): local judge + parallel rollout + optimized batch config 0735466 lebiraja Claude Haiku 4.5 commited on Apr 25
fix(rewards): LLM judge load balancing, premature query, keyword stuffing, SLA decay 341330e lebiraja Claude Sonnet 4.6 commited on Apr 25
docs: reorganize .md files into docs/ and rewrite README for Round 2 a8f3713 lebiraja commited on Apr 24
feat: hackathon improvements β benchmark dashboard, GRPO training pipeline, grader fixes b4289f9 lebiraja Claude Sonnet 4.6 commited on Apr 23
feat: complete CustomerSupportEnv RL environment for OpenEnv hackathon b722ec2 lebiraja JEFF2K07 lohithkrm Claude Sonnet 4.6 commited on Apr 8