1% Generated by `python -m wp30 sources audit` from literature/sources.csv (verified 2026-10-29) + curated core entries.23@misc{alabdulkareem2026swat, title={SwaT: Cross-Family KV Cache Transfer between Language Models}, author={Alabdulkareem, Abdulrahman and Tenison, Isabel and Zhang, Jun and Zhu, Yiyang and Katz, Boris and Gutfreund, Dan}, year={2026}, eprint={2610.15095}, archivePrefix={arXiv}, note={arXiv preprint, v1 (October 2026); repository Ar-Kareem/SwaT, no released checkpoint or licence (verified 2026-10-29)}}4@misc{zweiger2026compaction, title={Fast KV Compaction via Attention Matching}, author={Zweiger, Adam and Fu, Yilun and Guo, Han and Kim, Yoon}, year={2026}, eprint={2602.16284}, archivePrefix={arXiv}, note={arXiv preprint, v2 (May 2026); code adamzweiger/compaction, MIT}}5@inproceedings{fu2026c2c, title={Cache-to-Cache: Direct Semantic Communication Between Large Language Models}, author={Fu, Tianyu and others}, booktitle={International Conference on Learning Representations (ICLR)}, year={2026}, note={arXiv:2510.03215; code thu-nics/C2C, Apache-2.0; fuser checkpoints nics-efc/C2C\_Fuser}}6@inproceedings{zou2026latentmas, title={LatentMAS: Latent Collaboration in Multi-Agent Systems}, author={Zou, Jiaru and others}, booktitle={International Conference on Machine Learning (ICML)}, year={2026}, note={arXiv:2511.20639; code Gen-Verse/LatentMAS, Apache-2.0}}7@inproceedings{liu2024kivi, title={KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache}, author={Liu, Zirui and Yuan, Jiayi and Jin, Hongye and Zhong, Shaochen and Xu, Zhaozhuo and Braverman, Vladimir and Chen, Beidi and Hu, Xia}, booktitle={International Conference on Machine Learning (ICML)}, year={2024}, note={arXiv:2402.02750}}8@inproceedings{li2024snapkv, title={SnapKV: LLM Knows What You are Looking for Before Generation}, author={Li, Yuhong and Huang, Yingbing and Yang, Bowen and Venkitesh, Bharat and Locatelli, Acyr and Ye, Hanchen and Cai, Tianle and Lewis, Patrick and Chen, Deming}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2024}, note={arXiv:2404.14469; code FasterDecoding/SnapKV}}9@misc{cai2024pyramidkv, title={PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling}, author={Cai, Zefan and Zhang, Yichi and Gao, Bofei and Liu, Yuliang and Li, Yucheng and Liu, Tianyu and Lu, Keming and Xiong, Wayne and Dong, Yue and Hu, Junjie and Xiao, Wen}, year={2024}, eprint={2406.02069}, archivePrefix={arXiv}, note={v4 (May 2025); code Zefan-Cai/KVCache-Factory, MIT}}10@inproceedings{zhang2023h2o, title={H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models}, author={Zhang, Zhenyu and Sheng, Ying and Zhou, Tianyi and Chen, Tianlong and Zheng, Lianmin and Cai, Ruisi and Song, Zhao and Tian, Yuandong and R{\'e}, Christopher and Barrett, Clark and Wang, Zhangyang and Chen, Beidi}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2023}, note={arXiv:2306.14048}}11@inproceedings{xiao2024streamingllm, title={Efficient Streaming Language Models with Attention Sinks}, author={Xiao, Guangxuan and Tian, Yuandong and Chen, Beidi and Han, Song and Lewis, Mike}, booktitle={International Conference on Learning Representations (ICLR)}, year={2024}, note={arXiv:2309.17453}}12@inproceedings{pan2024llmlingua2, title={LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression}, author={Pan, Zhuoshi and Wu, Qianhui and Jiang, Huiqiang and Xia, Menglin and Luo, Xufang and Zhang, Jue and Lin, Qingwei and R{\"u}hle, Victor and Yang, Yuqing and Lin, Chin-Yew and Zhao, H. Vicky and Qiu, Lili and Zhang, Dongmei}, booktitle={Findings of the Association for Computational Linguistics: ACL 2024}, year={2024}, note={arXiv:2403.12968}}13@inproceedings{bai2024longbench, title={LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding}, author={Bai, Yushi and Lv, Xin and Zhang, Jiajie and Lyu, Hongchang and Tang, Jiankai and Huang, Zhidian and Du, Zhengxiao and Liu, Xiao and Zeng, Aohan and Hou, Lei and Dong, Yuxiao and Tang, Jie and Li, Juanzi}, booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, pages={3119--3137}, year={2024}, doi={10.18653/v1/2024.acl-long.172}}14@inproceedings{hsieh2024ruler, title={RULER: What's the Real Context Size of Your Long-Context Language Models?}, author={Hsieh, Cheng-Ping and Sun, Simeng and Kriman, Samuel and Acharya, Shantanu and Rekesh, Dima and Jia, Fei and Zhang, Yang and Ginsburg, Boris}, booktitle={First Conference on Language Modeling (COLM)}, year={2024}, note={arXiv:2404.06654}}15@misc{mlxlm2026, title={mlx-lm: Run LLMs with MLX}, author={{Apple ML Explore contributors}}, year={2026}, howpublished={\url{https://github.com/ml-explore/mlx-lm}}, note={v0.32.2 (16 October 2026), MIT}}16@misc{anthropic2026caching, title={Prompt caching}, author={{Anthropic}}, year={2026}, howpublished={\url{https://platform.claude.com/docs/en/build-with-claude/prompt-caching}}, note={accessed 2026-10-29}}17@misc{hf2026kvcache, title={KV cache strategies}, author={{Hugging Face}}, year={2026}, howpublished={\url{https://huggingface.co/docs/transformers/en/kv_cache}}, note={Transformers v5 documentation, accessed 2026-10-29}}18@misc{dasigi2021qasper, title={A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers}, author={Dasigi, Pradeep and Lo, Kyle and Beltagy, Iz and Cohan, Arman and Smith, Noah A. and Gardner, Matt}, year={2021}, note={NAACL 2021; QASPER, CC BY 4.0}}19@inproceedings{ho2020twowiki, title={Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps}, author={Ho, Xanh and Nguyen, Anh-Khoa Duong and Sugawara, Saku and Aizawa, Akiko}, booktitle={Proceedings of the 28th International Conference on Computational Linguistics (COLING)}, year={2020}}20@inproceedings{yang2018hotpotqa, title={HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering}, author={Yang, Zhilin and Qi, Peng and Zhang, Saizheng and Bengio, Yoshua and Cohen, William W. and Salakhutdinov, Ruslan and Manning, Christopher D.}, booktitle={EMNLP}, year={2018}}21@misc{qwen2.5, title={Qwen2.5 Technical Report}, author={{Qwen Team}}, year={2024}, eprint={2412.15115}, archivePrefix={arXiv}}22@misc{llama3, title={The Llama 3 Herd of Models}, author={{Llama Team, AI @ Meta}}, year={2024}, eprint={2407.21783}, archivePrefix={arXiv}}2324@misc{taekyung2026_heo2026, title={Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse}, author={Taekyung Heo; Rasoul Shafipour; Ritchie Zhao; Maximilian Golub; Mohammad Mahdi Kamani; Ritika Borkar; Makesh Tarun Chandran; Pantea Zardoshti; Bita Darvish Rouhani}, year={2026}, eprint={2608.03893}, archivePrefix={arXiv}, note={arXiv preprint; no venue stated; verification: arXiv export API metadata only (title/authors/dates/abstract); repo not checked}}25@misc{xingyu2026_qu2026, title={CacheBridge: Efficient Cross-Model KV Cache Transfer}, author={Xingyu Qu; Siyuan Lu; Zhiyu Chen; Sheng Wang; Tao Lin}, year={2026}, eprint={2609.00891}, archivePrefix={arXiv}, note={arXiv preprint; no venue stated; verification: arXiv export API metadata only}}26@misc{vincentdaniel2026_yun2026, title={Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs (HeteroFold)}, author={Vincent-Daniel Yun; Woosang Lim; Haneul Yoo; Sungjoo Yoo; Murali Annavaram; Sai Praneeth Karimireddy}, year={2026}, eprint={2609.32259}, archivePrefix={arXiv}, note={arXiv preprint; no venue stated; verification: arXiv export API metadata only}}27@misc{yi2026_li2026, title={A Universal Context-Reuse Layer for Cross-Model KV Sharing}, author={Yi Li; Dongming Jiang; Yi Zhao; Bingzhe Li}, year={2026}, eprint={2608.30963}, archivePrefix={arXiv}, note={arXiv preprint; no venue stated; verification: arXiv export API metadata only}}28@misc{xiangyu2025_shi2025, title={KVComm: Enabling Efficient LLM Communication through Selective KV Sharing}, author={Xiangyu Shi; Marco Chiesa; Gerald Q. Maguire; Dejan Kostic}, year={2025}, eprint={2510.03346}, archivePrefix={arXiv}, note={ICLR 2026 (arXiv Comments); verification: arXiv export API metadata only}}29@misc{hancheng2025_ye2025, title={KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems}, author={Hancheng Ye; Zhengqi Gao; Mingyuan Ma; Qinsi Wang; Yuzhe Fu; Ming-Yu Chung; Yueqian Lin; Zhijian Liu; Jianyi Zhang; Danyang Zhuo; Yiran Chen}, year={2025}, eprint={2510.12872}, archivePrefix={arXiv}, note={NeurIPS 2025 (arXiv Comments); verification: arXiv export API metadata only; repo URL from arXiv Comments, not fetched}}30@misc{yanwen2026_peng2026, title={StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems}, author={Yanwen Peng; Delvin Ce Zhang; Xi Wang; Nikolaos Aletras}, year={2026}, eprint={2608.13317}, archivePrefix={arXiv}, note={COLM 2026 (arXiv Comments; 18 pages); verification: arXiv export API metadata only}}31@misc{zhuoyun2025_du2025, title={Enabling Agents to Communicate Entirely in Latent Space (Interlat)}, author={Zhuoyun Du; Runze Wang; Huiyu Bai; Zouying Cao; Xiaoyong Zhu; Yu Cheng; Bo Zheng; Wei Chen; Haochao Ying}, year={2025}, eprint={2511.09149}, archivePrefix={arXiv}, note={Accepted to ACL 2026 (arXiv Comments); verification: arXiv export API metadata only}}32@misc{yuhan2024_liu2024, title={DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving}, author={Yuhan Liu; Yuyang Huang; Jiayi Yao; Shaoting Feng; Zhuohan Gu; Kuntai Du; Hanchen Li; Yihua Cheng; Junchen Jiang; Shan Lu; Madan Musuvathi; Esha Choukse}, year={2024}, eprint={2411.02820}, archivePrefix={arXiv}, note={arXiv; no venue in Comments (search snippet: NSDI 2026, unverified); verification: arXiv export API metadata only}}33@misc{yingzhuo2026_liu2026, title={Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems}, author={Yingzhuo Liu}, year={2026}, eprint={2606.05711}, archivePrefix={arXiv}, note={arXiv preprint (survey); no venue stated; verification: arXiv export API metadata only}}34@misc{simon2026_villani2026, title={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}, author={Simon P. Villani}, year={2026}, eprint={2609.25053}, archivePrefix={arXiv}, note={arXiv preprint (14 pages, Comments); verification: arXiv export API metadata only}}35@misc{zongqian2024_li2024, title={Prompt Compression for Large Language Models: A Survey}, author={Zongqian Li, Yinhong Liu, Yixuan Su, Nigel Collier}, year={2024}, eprint={2410.12388}, archivePrefix={arXiv}, note={arXiv (Comments empty); NAACL 2025 Long per search snippet (unverified); verification: arXiv page fetched; venue from search snippet only}}36@misc{yanyu2025_liu2025, title={KV Cache Compression for Inference Efficiency in LLMs: A Review}, author={Yanyu Liu, Jingying Fu, Sixiang Liu, Yitian Zou, You Fu, Jiehan Zhou, Shouhua Zhang}, year={2025}, eprint={2508.06297}, archivePrefix={arXiv}, note={arXiv preprint (Comments: 12 pages); verification: arXiv page fetched}}37@misc{neusha2025_javidnia2025, title={Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques}, author={Neusha Javidnia, Bita Darvish Rouhani, Farinaz Koushanfar}, year={2025}, eprint={2503.11816}, archivePrefix={arXiv}, note={IEEE CICC 2025 (invited; arXiv Comments); verification: arXiv page fetched}}38@misc{wei2025_gao2025, title={Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving}, author={Wei Gao, Xinyu Zhou, Peng Sun, Tianwei Zhang, Yonggang Wen}, year={2025}, eprint={2503.24000}, archivePrefix={arXiv}, note={MLSys 2025 (arXiv Comments); verification: arXiv page fetched}}39@misc{hancheng2025_ye2025, title={KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems}, author={Hancheng Ye, Zhengqi Gao, Mingyuan Ma, Qinsi Wang, Yuzhe Fu, Ming-Yu Chung, Yueqian Lin, Zhijian Liu, Jianyi Zhang, Danyang Zhuo, Yiran Chen}, year={2025}, eprint={2510.12872}, archivePrefix={arXiv}, note={NeurIPS 2025 (arXiv Comments: Accepted for publication in NeurIPS2025); verification: arXiv page fetched}}40@misc{zhuohang2026_bian2026, title={TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing}, author={Zhuohang Bian, Feiyang Wu, Chengrui Zhang, Hangcheng Dong, Yun Liang, Youwei Zhuo}, year={2026}, eprint={2604.03143}, archivePrefix={arXiv}, note={arXiv preprint under review; verification: arXiv page fetched}}41@misc{hyesung2026_jeon2026, title={LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents}, author={Hyesung Jeon, Hyeongju Ha, Jae-Joon Kim}, year={2026}, eprint={2602.01053}, archivePrefix={arXiv}, note={ICML 2026 Poster (arXiv journal-ref); verification: arXiv page fetched}}42@misc{yurui2026_chang2026, title={MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation}, author={Yurui Chang, Yiran Wu, Qingyun Wu, Lu Lin}, year={2026}, eprint={2603.23234}, archivePrefix={arXiv}, note={arXiv preprint (no venue stated); verification: arXiv page fetched}}43