CODI

A study by researchers testing the Coconut and CODI models found that these latent reasoning models barely use their hidden reasoning steps for logical tasks like PrOntoQA and ProsQA, with performance…

A new study from arXiv models latent chain-of-thought (CoT) reasoning as dynamical systems, revealing that CODI behaves as a stable attractor while COCONUT behaves as an unstable expanding system. Usi…

Researchers at the University of Oxford found that observable patterns in latent reasoning models, such as BFS-like frontiers and decodable arithmetic, also appear in control models lacking the propos…