#reasoning
2 posts tagged with "reasoning".
-
The Environment Became the Curriculum: Agent RL's Synthesis Turn
• 6 min readAgent RL's bottleneck moved from data to reward to the environment itself. The newest research tries to take humans out of environment-building entirely.
-
Where the Reward Goes: Agent RL's Reward-Design Split
• 5 min readRecent papers disagree on whether to reward agents per-turn or only at the end — and the answer reveals where RL for agents is actually headed.