Cites: Enabling Agents to Communicate Entirely in Latent Space
6 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.
- The Llama 3 Herd of Models
arxiv:2407.21783· evidence: title - Training Large Language Models to Reason in a Continuous Latent Space
arxiv:2412.06769· evidence: id - Communicating Activations Between Language Model Agents
arxiv:2501.14082· evidence: id - Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
arxiv:2502.05171· evidence: id - Cache-to-Cache: Direct Semantic Communication Between Large Language Models
arxiv:2510.03215· evidence: id - Reasoning Models Don't Always Say What They Think
url:anthropic.com/research/reasoning-models-dont-say-think· evidence: id