FIELD NOTES TOPIC
multi-agent llms
1 note, newest first.
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
The research examines the claim that multi-agent language models (LLMs) transmit 'latent thoughts' through relayed key-value caches instead of text, and finds significant evidence for this claim when the receiver needs…
