Where should Maya collect her pass on Friday, and what ID should she bring?

In multi-agent question answering, a large document collection can be split across agents, each with its own context. Answering a question requires combining information across those contexts.

With text communication, agents write messages summarising what they read. CacheBack lets them pass latent thoughts together with a subset of internal state selected for what the next agent needs. This example shows selected-state handoffs: three agents read separate documents in sequence, and a fourth agent produces the final answer.

The top row shows each agent’s input document: a booking confirmation, a location-change notice, then an ID policy. Agents 2 and 3 also receive the previous agent’s handoff; Agent 4 answers from the final handoff alone. The bottom row shows the messages generated by the text agents.