CondenseFlow: Scalable Latent Space Collaboration via Semantic Compression for Multi-Agent Systems

Full-state latent communication in LLM-based multi-agent systems offers richer semantics than text but suffers from memory overhead scaling linearly with collaboration rounds. We propose CondenseFlow , which introduces the Latent Thought Condenser (LTC) —a lightweight module using learnable semantic probes to compress KV caches into fixed-size representations, achieving O (1) communication complexity regardless of context length. We theoretically prove that compression error is bounded by attention concentration and accumulates controllably across rounds. On seven benchmarks spanning six models, Con-denseFlow reduces KV cache memory by over 99% and inference latency by approximately 20% compared to dense transfer with negligible accuracy degradation, while outperforming text-based methods by 1.7 percentage points on average across all configurations. Code is available at https://github.com/xxy33/ condenseflow .