reasoning-palette

【开发与工程】Overcome token-level randomness limitations in RL by shifting exploration to latent reasoning strategies. Train a VAE encoding diverse reasoning patterns, sample latents during RL, decode to prefix embeddings steering internal reasoning—enabling structured exploration across math, coding, and QA with interpretable, controllable behavior.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准