multi-turn RL

2 statements across 1 episodes · 1 bullish · 1 bearish · 1 people on the record · first statement May 9, 2025 by Will Brown · across every show →

Everything said about multi-turn RL, oldest first

May 9, 2025 positive
Insight
Long-horizon agent RL requires intermediate turn-level verification
“You probably want some kind of intermediate verification where you're not just waiting for the final answer at the end, But you want something like turn-level reward, potentially, where you want to be able to ensure that the model is getting credit for the mov…”
Will Brown May 9, 2025 ▶ 3:15 ⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)
May 9, 2025 negative
Insight
Current multi-turn RL research ignores discarded thinking tokens, breaking the math
“The existing paper people are writing about multi-turn RL are not actually incorporating this, and it kind of, like, breaks all the math.”
Will Brown May 9, 2025 ▶ 10:48 ⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.