XKV is introduced, which lifts all three restrictions on multi-agent LLM answering: learned-query attention pools both caches; self-attention over receiver-aligned layer tokens, with a learned layer map reconciling different depths, mixes the pooled summaries into a compact joint memory.
Abstract
Multi-agent LLM systems split work across models, so answering often requires knowledge that sits in another agent's context: a Sharer has encoded information that a Receiver needs to complete its task. They usually communicate by exchanging text, which puts autoregressive decoding on the critical path and reduces the exchange to a discrete message written without sight of the receiver's state. Recent latent protocols instead translate the sharer's key-value (KV) cache into the receiver's: C2C supports heterogeneous models but requires both to read the same input, while LCF-X removes this shared-context requirement through position-free sharer-cache pooling. Three restrictions remain: LCF-X compresses the sharer alone, supplies the same layer-local summary to every receiver position with no joint cross-layer memory to retrieve from, and assumes matched layer count and KV geometry. We introduce XKV, which lifts all three: learned-query attention pools both caches; self-attention over receiver-aligned layer tokens, with a learned layer map reconciling different depths, mixes the pooled summaries into a compact joint memory; and a shared position decoder lets every raw receiver cache position retrieve its own per-head-gated residual in the receiver's native KV geometry. Both models stay frozen and may differ in family, depth, KV-head count, head dimension, and tokenizer; only the translator is trained. Across 45 dataset-model-pair settings (six heterogeneous and three same-model ordered pairings, five datasets), XKV attains the highest macro score and best average rank, improving on LCF-X on every dataset (by 4.6 exact-match and 4.2 F1 points on ROPES) and surpassing text communication on four of the five, while training 76% fewer parameters and translating a cache pair 10.3x faster (5.8 vs. 59.9 ms); end to end, XKV is 26% faster than LCF-X and 6.8x faster than text communication.
CacheBack is a simple, robust, training-free instance of receiver conditioning based on the sender's attention weights that improves accuracy and reduces median task-completion latency on FanOutQA and shows comparable improvements across model families that span dense Transformers, Mamba-attention hybrids, and sliding-...
M. Rossi, Prajwal Raghunath, Hao Xuan et al.· 0 citations
This work proposes LatCom, a cross-agent latent compression framework for efficient multi-agent latent collaboration, which achieves an average 2.46x inference speed-up over LatentMAS and reduces output token usage by 70.3% while maintaining comparable average accuracy.
Shi-Nan Zhang, Tao Zhang, Qi-Hui Zhu et al.· 0 citations
XBRIDGE is proposed, a decode-free communication protocol that outperforms text-based communication on all seven tasks for each model pair while achieving 11x lower latency, and in a same-architecture setting it also exceeds a KV-sharing baseline on six of seven tasks.
Wooseong Yang, Wei-Chieh Huang, Wei-Zhi Zhang et al.· 3 citations
Results show that HeteroFold enables efficient cross-family KV reuse without receiver prefill, and achieves the best cache-transfer performance on all four long-context benchmarks and most short-context settings.
ShareMem is introduced, a memory architecture that shares reusable experience while grounding its application in the receiving user's own preferences, and improves step success, average task success, and dialogue-macro coding scores, respectively, over matched user-local memory across all four models.
This work demonstrates useful persistent hybrid-state transfer across one architecture-matched Qwen3.5 4B-to-9B sibling pair, the first demonstrated cross-model handoff of persistent recurrent inference state between differently sized hybrid language models without target prefix replay.
Simon P. Villani· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.