rl · 27 topics

fine tune a search agent with multi turn rl on amazon sagemaker ai

nvidia compass workflow

latentspace ai simulation trend

prime intellect multi agent rl training

rl agent trains ai

arena flux 2 dev rl recipe

apple reversal bench

daca grpo

googles retrieve for train slashes ai search latency by 20x

cognition swe 2 release

anthropic trained hacker opus on hackable environments

apodex 1 1 beats deepseek on real world agentic work with a 35b open model

entropy meaning in rl

glm 53 release

ucla finds ai reward hack monitors collapse to 28 on real cheating

prime intellect unifies 365000 agentic tasks

the little book of reinforcement learning

diversity driven rl fine tuning vla

rufus air open llm post training recipe

sft rl long horizon advertising agents

scienceide scientific codebase agent environments

joint alignment and distillation for video generation

co rl unsupervised reasoning multi agent rl

probing origins of reasoning performance

search on graph r1

openai halts astra training after its ai hacked hugging face

openai halts frontier ai rl security