[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-let-llms-skip-language-and-talk-in-raw-cache":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},7016,"researchers-let-llms-skip-language-and-talk-in-raw-cache","Researchers Let LLMs Skip Language and Talk in Raw Cache","A new paper proposes letting language models exchange internal cache states directly, skipping the text they normally use to talk to each other.","A new arXiv paper proposes letting large language models swap their internal cache states instead of talking to each other only in plain text.\n\nThe paper, titled \"Cache-to-Cache: Direct Semantic Communication Between LLMs,\" was posted to arXiv and has been circulating in developer discussions, gathering modest engagement so far. The core idea: when one model currently needs another model's help, it generates text, and the second model has to read that text and re-encode it into its own internal representation before it can use it. The authors propose skipping that round trip by passing the KV-cache - the model's internal semantic state - directly between models instead.\n\nThis matters because multi-model pipelines are becoming a default architecture, not a novelty. Chains of LLMs calling other LLMs, or agent frameworks that hand tasks between specialized models, all currently rely on text as the connective tissue. Text is legible but wasteful: generating it costs compute, and reading it back in loses some of the nuance the first model actually had. A cache-level interface is a bet that speed and fidelity matter more than having a human-readable log of what one model told another.\n\nThat tradeoff cuts both ways. The same plain-text interface this approach treats as overhead is also the only place a developer can currently see what's going wrong when a multi-model system fails. Skip it, and debugging gets harder even as throughput improves. With only 55 points and 11 comments in early discussion, this is still a niche research idea, not a shipped feature - worth watching, not worth building around yet.","[\"llms\",\"ai-research\",\"multi-agent-systems\",\"arxiv\"]","2026-09-18T18:55:35.000Z","2026-09-19T07:04:03.794Z","2026-09-19T07:04:15.731Z","published",null,[],"ai",[26,27,28,29],"llms","ai-research","multi-agent-systems","arxiv",[31],{"name":32,"url":33},"Hacker News","https:\u002F\u002Farxiv.org\u002Fabs\u002F2510.03215",0,{"sections":36},[37,41,46,51,56,61,66,71,76,81,86,91,96,101],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",4114,"2026-09-19T18:33:46.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":45},"Security","security",673,"2026-09-19T17:30:00.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Policy","policy",345,"2026-09-19T19:22:20.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",156,"2026-09-19T11:00:00.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Science","science",129,"2026-09-19T19:45:00.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Dev Tools","dev-tools",78,"2026-09-18T04:00:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"General","general",42,"2026-09-18T22:35:10.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]