Overview

KV-cache reuse studies how language models can retain and reuse attention states instead of repeatedly processing the same documents, conversation history, or shared context, reducing latency and memory costs in retrieval-augmented generation, long-context, and multi-agent settings. Approaches include exact-prefix caching, selective recomputation and cache repair, compression, position-invariant reuse, and transferring cache states across models; serving systems add scheduling and storage tiers to make reuse practical. A central challenge is preserving answer quality when cached states are used in a different position, context, model, or request order, so many methods combine reuse with targeted correction or recomputation. Evaluation remains sensitive to workload and measurement choices, and safety, privacy, and timing leakage are additional concerns when caches are shared.

Latest papers

CardsList

81 papers9 papers in the last four weeks, down 61% on the four weeks before. 0.1% of all new papers.

  1. HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse

    Nov 12, 2026Saehun Chun, Wonje Choi, Jinwoo Jang +2Memory-Augmented AgentsKV-Cache Reuse

  2. Where Should a KV-Cache Repair Budget Go? Distractor Structure and Contextual Compatibility in Non-Prefix Reuse

    Nov 4, 2026Yuxing Peng, Zhiqing Tang, Weijia JiaKV-Cache ReuseKV-Cache Management

  3. Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning

    Nov 3, 2026Tianming Sha, Junnan Li, Siqi ZhaoMulti-Agent Reinforcement LearningRL for LLM Agents

  4. CacheWeave: Learning to Recompute for Efficient Position-Independent KV Caching

    Nov 1, 2026Yueyang Pan, Qianchao Zhu, Yuliang Liu +2LLM Inference AccelerationKV-Cache Reuse

  5. ACCT: Asymmetric Cross-LLM Context Transfer

    Oct 30, 2026Yuzhe Liu, Haolin Tian, Tonghan WangKV-Cache ReuseLLM Inference Acceleration

  6. Shared Context, Separate Engines: Stateful Streaming Inference for Multimodal LLMs on Edge SoCs

    Oct 26, 2026Yilong Li, Chengpo Yan, Yijing Zeng +3Efficient VLM InferenceVLM Inference

  7. BeNice! Closing Looping's Inference-Memory Gap via KV-Sharing

    Oct 22, 2026Hayden Prairie, Jacob M. Ryan, Taylor Berg-Kirkpatrick +1KV-Cache ReuseMemory-Efficient Inference

  8. System X: An LLM Decision Model That Replies from Its Own KV Cache

    Oct 18, 2026Syed Usama Khalid Bukhari, Syed Safwan Khalid, Muhammad AamirLLM Decision-MakingKV-Cache Reuse

  9. Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches

    Oct 15, 2026Adam Deng, Shicheng Liu, Yada ZhuKV-Cache ReuseMulti-Agent LLM Systems

  10. LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems

    Oct 13, 2026Zhiwei Chen, Zhongtao Rao, Waikit Xiu +4KV-Cache ReuseMulti-Agent LLM Systems

  11. Hashrope: A Persistent Data Structure for Mechanisms of LLM Context Management

    Oct 12, 2026Muntaser Syed, Ameerah Alsulami, Marius SilaghiLLM Context ManagementLLM Inference Acceleration

  12. CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff

    Oct 11, 2026Haomiao Qiu, Yining Tang, Zijia Song +3KV-Cache TransferLLM Serving

  13. KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse

    Oct 9, 2026Taiga Ikeda, Daisuke Miyashita, Jun DeguchiKV-Cache ReuseKV-Cache Management

  14. RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation

    Oct 8, 2026Sreetama Sarkar, Saptarshi Mitra, Sitao Huang +2KV-Cache ReuseLLM Inference Acceleration

  15. KV2^2: A Self-Refining KV Cache

    Oct 2, 2026Johannes Wesch, Danni Liu, Jan NiehuesKV-Cache CompressionKV-Cache Eviction

  16. ATTUNER: Recomputation-Free Agentic Context KV Reuse

    Sep 29, 2026Xinghao Chen, Junnan Dong, Cai Ke +8KV-Cache ReuseLLM Inference Acceleration

  17. Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs

    Sep 28, 2026Zhengxiang Huang, Shengheng Chen, Chaoyue Niu +6AI Accelerator InferenceOn-Device Language Model Inference

  18. KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems

    Sep 28, 2026Hyesung Jeon, Hyeongju Ha, Seoyoung Lee +2Multi-Agent LLM SystemsKV-Cache Management

  19. PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction

    Sep 28, 2026Hyesung Jeon, Hyeongju Ha, Jae-Joon KimMulti-Agent LLM SystemsMemory-Efficient Inference

  20. RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse

    Sep 27, 2026Ruoling Qi, Yirui Liu, Xuaner Wu +5Retrieval-Augmented GenerationKV-Cache Management

  21. Budgeted Cache Repair for Cross-Context KV-Cache Reuse

    Sep 27, 2026Haeyong Kang, Chang D. YooKV-Cache ManagementKV-Cache Reuse