RecursiveMAS: Stanford's Multi-Agent Breakthrough
Stanford/UIUC/NVIDIA/MIT team introduces RecursiveMAS: multi-agent systems that pass latent representations instead of text. +8.3% accuracy, 2.4x faster, 75% fewer tokens.
TOPIC_INDEX
2 published entries in this topic.
Stanford/UIUC/NVIDIA/MIT team introduces RecursiveMAS: multi-agent systems that pass latent representations instead of text. +8.3% accuracy, 2.4x faster, 75% fewer tokens.
OpenBMB's VoxCPM2 breaks the discrete-token trap with tokenizer-free TTS. 30 languages, voice design, and similarity scores that beat ElevenLabs by 15+ points.