Reasoning Model Caching

  • Last Updated 2 May, 2026
  • by David Spuler, Ph.D.

Research on Reasoning Model Caching

Research papers include:

  • Akshat Ramachandran, Marina Neseem, Charbel Sakr, Rangharajan Venkatesan, Brucek Khailany, Tushar Krishna, 1 Oct 2025, ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models, https://arxiv.org/abs/2510.01290
  • Anna Kuzina, Maciej Pioro, Paul N. Whatmough, Babak Ehteshami Bejnordi, 2 Oct 2025, KaVa: Latent Reasoning via Compressed KV-Cache Distillation, https://arxiv.org/abs/2510.02312
  • Haoyue Zhang, Hualei Zhang, Xiaosong Ma, Jie Zhang, Song Guo, 14 Oct 2025, LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning, https://arxiv.org/abs/2506.15969
  • Yu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong, Wen Xiao, 23 Oct 2025, Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning, https://arxiv.org/abs/2410.19258
  • Adnan Oomerjee, Zafeirios Fountas, Haitham Bou-Ammar, Jun Wang, 26 Sep 2025, Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning, https://arxiv.org/abs/2505.16950
  • Kaiwen Chen, Xin Tan, Minchen Yu, Hong Xu, 29 Jul 2025, MemShare: Memory Efficient Inference for Large Reasoning Models through KV Cache Reuse, https://arxiv.org/abs/2507.21433
  • Mingyuan Wu, Jize Jiang, Haozhen Zheng, Meitang Li, Zhaoheng Li, Beitong Tian, Bo Chen, Yongjoo Park, Minjia Zhang, Chengxiang Zhai, Klara Nahrstedt, 19 Sep 2025, Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning, https://arxiv.org/abs/2502.20587
  • Varun Chillara, Dylan Kline, Christopher Alvares, Evan Wooten, Huan Yang, Shlok Khetan, Cade Bauer, Tré Guillory, Tanishka Shah, Yashodhara Dhariwal, Volodymyr Pavlov, George Popstefanov, 1 Feb 2026 (v2), SemanticALLI: Caching Reasoning, Not Just Responses, in Agentic Systems, https://arxiv.org/abs/2601.16286
  • Hang Lv, Sheng Liang, Hongchao Gu, Wei Guo, Defu Lian, Yong Liu, Hao Wang, Enhong Chen, 16 Apr 2026, IE as Cache: Information Extraction Enhanced Agentic Reasoning, https://arxiv.org/abs/2604.14930

More AI Research Topics

Read more about: