source_id,title,authors,venue_status,year,url,access_date,revision,repository_url,commit,checkpoint_availability,supported_backends,license,relevance,reproduction_status,verification
swat2026,"Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families","Abdulrahman Alabdulkareem; Irene Tenison; Yang Zhang; Yada Zhu; Boris Katz; Dan Gutfreund","arXiv preprint (cs.LG); no venue stated",2026,https://arxiv.org/abs/2610.15095,2026-10-29,"v1 (2026-10-10); latest v1",https://github.com/Ar-Kareem/SwaT,ae2de2285caf82f4d500526bf6e6992747b98eea,"none released; mapper (~300M params) must be trained locally (<1 GPU-day, 2 GPUs); default pair Granite-3.3-8B -> SmolLM3-3B","PyTorch 2.6.0 + HF Transformers 5.2.0; multi-GPU CUDA; GPU model not stated; no vLLM/MLX/MPS mention","none (no LICENSE file, GitHub API license=null)","Primary: first prefill-free cross-family KV transfer; translate-then-AM-compact pipeline (Eq. 8); receiver needs token IDs of source text but no prefill",pending,"verified: arXiv abs+API+HTML, GitHub API, raw README/requirements; unverified: GPU type, MPS support"
compaction2026,"Fast KV Compaction via Attention Matching","Adam Zweiger; Xinghong Fu; Han Guo; Yoon Kim","arXiv preprint (cs.LG); no venue stated",2026,https://arxiv.org/abs/2602.16284,2026-10-29,"v1 (2026-02-18); latest v2 (2026-05-26)",https://github.com/adamzweiger/compaction,2020f6d37940fe013e7e7f1ebf409e5d107c5670,"not applicable (training-free); only per-model head-budget JSON files shipped; demo Qwen/Qwen3-4B","PyTorch 2.8.0 + HF Transformers 4.57.1 + vLLM 0.11.0 (query generation) + accelerate; Python 3.12; H100/H200 in paper; no MLX/MPS mention",MIT,"Primary: same-model latent KV compaction used by SwaT+AM; closed-form keys/values/bias from reference queries; no cross-model claim",pending,"verified: arXiv abs+API+HTML, GitHub API, LICENSE, requirements; unverified: MPS support"
c2c2025,"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","Tianyu Fu; Zihan Min; Hanling Zhang; Jichao Yan; Guohao Dai; Wanli Ouyang; Yu Wang","Published in ICLR'26 (arXiv Comments); cs.CL cs.LG",2025,https://arxiv.org/abs/2510.03215,2026-10-29,"v1 (2025-10-03); latest v2 (2026-03-02)",https://github.com/thu-nics/C2C,5eac72b90faf7b3dc2638e874fe7cba1e74c8bcf,"released: https://huggingface.co/nics-efc/C2C_Fuser (apache-2.0; 7 fuser pairs: Qwen3-0.6B<-Qwen2.5-0.5B-Instruct, Qwen3-0.6B<-Llama-3.2-1B-Instruct, Qwen3-0.6B<-Qwen2.5-Math-1.5B, Qwen3-0.6B<-Qwen3-4B, Qwen3-0.6B<-Qwen3-4B-Base, Qwen3-1.7B<-Qwen2.5-1.5B-Instruct, Qwen3-8B<-Qwen2.5-7B-Instruct); demo huggingface.co/spaces/nics-efc/C2C_demo","PyTorch 2.6.0 + HF Transformers 4.52.4; CUDA (examples device=cuda, linux-64 conda env); A100 timing; no vLLM/MLX/MPS mention","Apache-2.0 (LICENSE; pyproject classifier says MIT - discrepancy)","Primary: cross-family KV fusion via trained per-layer fuser with gate; receiver still prefills source text; +3.1-5.4% vs T2T, 2.5x latency",pending,"verified: arXiv abs+API+HTML, GitHub API, raw README/pyproject, HF API model repo; unverified: training GPU type, MPS support"
latentmas2025,"Latent Collaboration in Multi-Agent Systems","Jiaru Zou; Ruizhong Qiu; Gaotang Li; Xiyuan Yang; Katherine Tieu; Pan Lu; Ke Shen; Hanghang Tong; Yejin Choi; Jingrui He; James Zou; Mengdi Wang; Ling Yang","ICML 2026 Spotlight (arXiv Comments + repo); cs.CL cs.AI cs.LG",2025,https://arxiv.org/abs/2511.20639,2026-10-29,"v1 (2025-11-25); v2 (2025-12-08); v3 (2026-06-01); latest v4 (2026-08-03)",https://github.com/Gen-Verse/LatentMAS,9a9e4d331eb11430bd9e64754c6b252b06d73031,"none (training-free; stock HF models Qwen3-4B/8B/14B, Llama-3 3B/8B); experiment logs on Google Drive","PyTorch + HF Transformers (unpinned); optional patched vLLM backend; 8x A100-80G in paper; no MLX/MPS mention",Apache-2.0,"Primary: training-free latent thoughts + shared KV working memory between same-architecture agents; lossless-transfer theorem; homogeneous agents only",pending,"verified: arXiv abs+API+HTML, GitHub API, LICENSE, requirements; unverified: dedicated limitations section not located, MPS support"
heo2026,"Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse","Taekyung Heo; Rasoul Shafipour; Ritchie Zhao; Maximilian Golub; Mohammad Mahdi Kamani; Ritika Borkar; Makesh Tarun Chandran; Pantea Zardoshti; Bita Darvish Rouhani","arXiv preprint; no venue stated",2026,https://arxiv.org/abs/2608.03893,2026-10-29,"v1 (2026-08-04); latest v1",unverified,unverified,unverified,unverified,unverified,"Same-family closed-form ridge KV mapper (Qwen3 14B->32B); cited by SwaT as 'Closed Form' baseline",pending,"arXiv export API metadata only (title/authors/dates/abstract); repo not checked"
qu2026,"CacheBridge: Efficient Cross-Model KV Cache Transfer","Xingyu Qu; Siyuan Lu; Zhiyu Chen; Sheng Wang; Tao Lin","arXiv preprint; no venue stated",2026,https://arxiv.org/abs/2609.00891,2026-10-29,"v1 (2026-09-01); latest v1",unverified,unverified,unverified,unverified,unverified,"Per-head architecture-indexed mapper improving Heo et al.; same-family; cited by SwaT",pending,"arXiv export API metadata only"
yun2026,"Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs (HeteroFold)","Vincent-Daniel Yun; Woosang Lim; Haneul Yoo; Sungjoo Yoo; Murali Annavaram; Sai Praneeth Karimireddy","arXiv preprint; no venue stated",2026,https://arxiv.org/abs/2609.32259,2026-10-29,"v1 (2026-09-26); latest v2 (2026-09-29)",unverified,unverified,unverified,unverified,unverified,"Direct competitor to SwaT: prefill-free cross-family transfer with frozen models (Llama-3.1-8B -> Ministral-3-14B)",pending,"arXiv export API metadata only"
li2026,"A Universal Context-Reuse Layer for Cross-Model KV Sharing","Yi Li; Dongming Jiang; Yi Zhao; Bingzhe Li","arXiv preprint; no venue stated",2026,https://arxiv.org/abs/2608.30963,2026-10-29,"v1 (2026-08-31); latest v1",unverified,unverified,unverified,unverified,unverified,"Serving-system layer translating KV state across models differing in scale/architecture/tokenizer/family",pending,"arXiv export API metadata only"
shi2025,"KVComm: Enabling Efficient LLM Communication through Selective KV Sharing","Xiangyu Shi; Marco Chiesa; Gerald Q. Maguire; Dejan Kostic","ICLR 2026 (arXiv Comments)",2025,https://arxiv.org/abs/2510.03346,2026-10-29,"v1 (2025-10-02); latest v3 (2026-02-22)",unverified,unverified,unverified,unverified,unverified,"Selective layer-wise KV-pair sharing as inter-LLM channel; contemporaneous alternative to C2C",pending,"arXiv export API metadata only"
ye2025,"KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems","Hancheng Ye; Zhengqi Gao; Mingyuan Ma; Qinsi Wang; Yuzhe Fu; Ming-Yu Chung; Yueqian Lin; Zhijian Liu; Jianyi Zhang; Danyang Zhuo; Yiran Chen","NeurIPS 2025 (arXiv Comments)",2025,https://arxiv.org/abs/2510.12872,2026-10-29,"v1 (2025-10-14); latest v2 (2025-11-01)",https://github.com/FastMAS/KVCOMM,unverified,unverified,unverified,unverified,"Same-model multi-agent KV reuse with context-aware offsetting (~6.7x prefill speedup); efficiency baseline, not cross-model",pending,"arXiv export API metadata only; repo URL from arXiv Comments, not fetched"
peng2026,"StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems","Yanwen Peng; Delvin Ce Zhang; Xi Wang; Nikolaos Aletras","COLM 2026 (arXiv Comments; 18 pages)",2026,https://arxiv.org/abs/2608.13317,2026-10-29,"v1 (2026-08-13); latest v1",unverified,unverified,unverified,unverified,unverified,"Training-free orthogonal alignment of sender final-layer hidden states to receiver input space; cross-model latent channel without projectors",pending,"arXiv export API metadata only"
du2025,"Enabling Agents to Communicate Entirely in Latent Space (Interlat)","Zhuoyun Du; Runze Wang; Huiyu Bai; Zouying Cao; Xiaoyong Zhu; Yu Cheng; Bo Zheng; Wei Chen; Haochao Ying","Accepted to ACL 2026 (arXiv Comments)",2025,https://arxiv.org/abs/2511.09149,2026-10-29,"v1 (2025-11-12); latest v5 (2026-07-13)",unverified,unverified,unverified,unverified,unverified,"Last-hidden-state latent communication with learned compression; early latent-MAS baseline",pending,"arXiv export API metadata only"
liu2024,"DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving","Yuhan Liu; Yuyang Huang; Jiayi Yao; Shaoting Feng; Zhuohan Gu; Kuntai Du; Hanchen Li; Yihua Cheng; Junchen Jiang; Shan Lu; Madan Musuvathi; Esha Choukse","arXiv; no venue in Comments (search snippet: NSDI 2026, unverified)",2024,https://arxiv.org/abs/2411.02820,2026-10-29,"v1 (2024-11-05); latest v4 (2025-07-14)",unverified,unverified,unverified,unverified,unverified,"Same-architecture cross-LLM KV reuse (recompute few layers); precedent cited by SwaT",pending,"arXiv export API metadata only"
liu2026,"Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems","Yingzhuo Liu","arXiv preprint (survey); no venue stated",2026,https://arxiv.org/abs/2606.05711,2026-10-29,"v1 (2026-06-04); latest v3 (2026-07-15)",unverified,unverified,unverified,unverified,unverified,"Survey of 18 latent-communication methods 2024-2026; taxonomy for related work",pending,"arXiv export API metadata only"
villani2026,"LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay","Simon P. Villani","arXiv preprint (14 pages, Comments)",2026,https://arxiv.org/abs/2609.25053,2026-10-29,"v1 (2026-09-07); latest v1",unverified,unverified,unverified,unverified,unverified,"Transfers GDN recurrent state + KV across Qwen3.5 4B->9B hybrid siblings without prefix replay",pending,"arXiv export API metadata only"