@VaishShrivas on Backlist

1 appearance on the backlist front page in the last 30 days.

57.

ECHO paper + code are now live! We open-sourced a small SkyRL-based implementation of "world loss" for terminal-agent RL. GRPO trains on what the agent did. ECHO also learns from what the terminal said next. Same rollout. Same policy fo

by (Vaish Shrivastava) · backlist 2026-05-27 · rubric 88.0