Open Source Radar
Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).
89stars
9forks
1issues
2026since
Star historydaily snapshots by VibeCrowd
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).