Showing cs.MAShow all
2 papers · 1 filter
cs.MA2026
Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning
Carlos Baquero, Luís Brito
Multi-agent latent reasoning composes agents' KV-caches into one context for a final agent. Prior work (Agent Primitives) does this by concatenating caches along the sequence axis…
cs.MA2026
When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration
Luís Brito, Carlos Baquero
LLM agents can share more than text. In some systems, an agent can send a short visible message while also passing its full KV-cache state to another model. This hidden state can h…