Skip to main content
Search

# Multi-Agent Latent Reasoning

1 related articles

Subscribe to updates
  1. arXiv

    CanonicalMerge turns multi-agent KV-cache merging into a convergent replicated state via content-determined ordering, matching the best BagMerge ordering on a partitioned-reasoning benchmark

    The work models KV-cache exchange in multi-agent latent reasoning as a convergent replicated state: CanonicalMerge fixes the layout by a content-determined ordering (mean K-norm at a middle layer), making the merged cache byte-identical under any input permutation (verified on synthetic tensors with N<=5 and bit-for-bit on real Qwen3-1.7B and Qwen3-4B KV state), and on a partitioned-reasoning benchmark it matches the best BagMerge ordering without knowing which it is (within 4 points in all 12 cells at 1.7B, same picture at 4B, and tracking the best ordering on Llama-3.1-8B where the gap grows to 19 points), while being the best cache-level method on HotpotQA (n=200) and MuSiQue.

You’re all caught up