这篇论文给出了一套错配缓存审计法，对比LatentMAS、KVComm、C2C后发现，基准涨分不等于真在传潜在思维。
多智能体LLM系统中，智能体间通过中继KV缓存而非文本交换信息。论文用错配缓存、清零缓存和矩匹配随机缓存做因果审计，覆盖LatentMAS、KVComm、C2C等系统。在接收方需要发送方私有信息时，主骨干上的相关中继达到100%，无关中继仅23%-25%。在不需要私有信息时，预注册五种子协议在GSM8K、ARC-Challenge、MedQA上显示等效性差异在2.8个点以内。清零中继造成14.7个点下降，而错配缓存仅0.4个点，说明缓存效应不一定来自示例配对。
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a claim about \emph{which} example's cache is relayed, not merely that one is. We audit it causally in released systems. The cache is replaced with deranged (mismatched-example), zeroed, and moment-matched random counterparts, under two regimes defined by whether the receiver needs the sender's private information. Where it does, the battery reads ceiling: 100\% against 23--25\% for answer-irrelevant relays on the primary backbone, a contrast replicated across three families, five checkpoints, and a prose document-QA surface. Where it does not, a pre-registered five-seed protocol establishes equivalence within 2.8 points, a margin anchored to the audited system's reported gain, under Holm-corrected TOST on GSM8K and ARC-Challenge across three Qwen3 scales and on MedQA at 8B (one cell shows a small detected advantage inside the margin); a second family shows no detected advantage. A large cache effect need not be a pairing effect. In one natural cell, zeroing the relay costs 14.7 points; a mismatched cache, 0.4. Nor is need sufficient: under the same test, delivered channels span ceiling (LatentMAS's native relay), partial (KVComm's layer subset), and no detected example-specific transfer (C2C's released projector). Benchmark deltas do not by themselves establish latent-thought transmission; establishing it takes a mismatched-cache audit, which we release.