⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)

Lays out what is missing for open models to match o3-style agents (browsing, coding, long horizons) and which RL problems are solvable, helping you judge where open agent models are headed.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• videoWhy Every Agent needs Open Source Cloud Sandboxes
• videoTerminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
• video[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI
• video⚡️ Reverse Engineering OpenAI's Training Data — Pratyush Maini, Datology

• video⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime IntellectLatent Space
• videoThe Breakthroughs Needed for AGI Have Already Been Made: OpenAI Former Research Head Bob McGrewSequoia Capital
• videoWhat does the next training paradigm look like?Dwarkesh Patel

Checking sign-in…

Loading comments…