No AI summary available for this article.
Why It Matters
Chain-of-thought reasoning unfolds in discrete token space: each step is committed as text, errors propagate, and eliciting good traces presupposes traces to imitate.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Chain-of-thought reasoning unfolds in discrete token space: each step is committed as text, errors propagate, and eliciting good traces presupposes traces to imitate. Reasoning instead in a model's continuous representation space - where intermediate states are vectors rather than words - sidesteps these constraints, but leaves open how those latent states should be computed. We approach this along two axes. First, we keep a large language model (LLM) frozen and use it for what it is already good at - modeling and decoding sequences - while a small auxiliary network supplies continuous latent...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.01117v1 · Indexed about 2 hours ago