The paper introduces cache engineering for large language model agents, enabling direct control over the active key-value cache without altering the trajectory or triggering costly re-prefilling. It defines cache operations such as drop and repos, formalizes their effects, and addresses the challenge of history-dependent cache states. The authors co-design a stateless AKV serving engine that manages stateful cache reuse, eviction, and restoration, achieving significant performance and cost improvements over traditional summarization methods.
By Tianyu Fu, Ruoxi Wang, Zihan Min, Zhongqi Ren, Zhihao Li, Tengxuan Liu, Shengxu Mu, Hanling Zhang, Yu Wang
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
By Zhikang Xie, Xichen Ye, Yifan Wu, Haoshen Yu, Li chenan, Peizhu Gong, Weizhong Zhang, Cheng Jin
arXiv:2610.08811v1 Announce Type: new
Abstract: As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing me...
By Linfeng Dong
arXiv:2607. 20495v1 Announce Type: new Abstract: Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries.
By Anas Mohamed, Kaizan Haque, Azal Ahmad Khan, Chetan Sharma, Shuwen Ge, Ali Anwar
arXiv:2609.34060v2 Announce Type: replace
Abstract: Prompt-specialized multi-agent systems enable multiple agents to share a model while performing complementary roles to solve complex tasks. However...
By Hyesung Jeon, Hyeongju Ha, Seoyoung Lee, Beomseok Kang, Jae-Joon Kim
arXiv:2610.17338v1 Announce Type: new
Abstract: Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computatio...
By Han Yu, Wenhui Zhu, Jincheng Cao, Rui Cai, Yuanda Xu, Zhengze Zhou, Xiwen Chen, Hao Wang, Xuanzhao Dong, Han Shi, Menglin Zhou, Shayan Mohajer Hamidi, Lin Su, Mina Razghandi, Sayan Ghosh, Qing Lan, Rohit Jain, Alborz Geramifard
arXiv:2610.07863v1 Announce Type: cross
Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with s...
By Yupeng Su, Jiayi Tian, Zheng Zhang, Souvik Kundu
arXiv:2607. 23809v1 Announce Type: new Abstract: Agentic tasks are inherently long-horizon and multi-turn, constantly accumulating context through interactions with the environment.
By Xiaochuan Li, Ryan Ming, Meng Chu, Shuai Shao, Rong Jin, Chenyan Xiong
arXiv:2608.30647v1 Announce Type: cross
Abstract: Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at ea...
By Asa Shepard
The paper introduces Dynamic Tool Output Compression (DTOC), a framework that manages context in large‑language‑model agents by storing full tool outputs in external memory and inserting compact placeholders into the active context. DTOC treats context updates as explicit, reversible operations within the agent’s reasoning loop, allowing selective reconstruction of compressed outputs when needed. Experiments on the DeepSWE benchmark show that for responsive models such as Sonnet 4.6 and GPT‑5.4, DTOC reduces input tokens and agent steps while significantly improving solve rates and lowering cost per solved task, with ablation studies confirming the importance of reversibility for maintaining performance.
By Abhay Chaturvedi, Shreya Bhattacharya, Rashmika Gopalkrishnan, Peter van der Putten
The paper introduces TokenWorth, a lightweight framework that learns the value of past experiences for self-improving agents operating under strict resource constraints. By using sparse execution feedback, TokenWorth guides both retrieval and memory management without updating the core model, enabling agents to adaptively reuse only the most beneficial experiences. Experiments on LifelongAgentBench show that TokenWorth outperforms existing lifelong-memory methods in task success while minimizing output tokens within the given budgets.
By Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang, Han-Jia Ye
arXiv:2609.37988v1 Announce Type: new
Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This i...
By Joao Monteiro, Louis B\'ethune, Anastasiia Filippova, Sonia Laguna, David Grangier, Marco Cuturi