When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs

[2608.04893] When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs Skip to main content Search Submit Donate Log in Computer Science > Cryptography and Security arXiv:2608.04893 (cs) [Submitted on 5 Aug 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs Authors: Jiaming Cheng , Subhransu Das , Rajiv Ramnath View PDF HTML (experimental) Abstract: 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 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. Comments: v2: metadata only, fixed abstract formatting Subjects: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2608.04893 [cs.CR] (or arXiv:2608.04893v2 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2608.04893 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiaming Cheng [ view email ] [v1] Wed, 5 Aug 2026 14:18:42 UTC (676 KB) [v2] Thu, 27 Aug 2026 04:35:16 UTC (676 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CR < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.LG References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs#674514
• When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs#429262
• ePACT: Energy-Performance-Aware Commitment Tracking for LLM Serving#1160971
• ePACT: Energy-Performance-Aware Commitment Tracking for LLM Serving#1157055
• Charged but Not Activated: Attitude-Behaviour Gaps in Energy Infrastructure Responses#352121