Tianyu Fu, Ruoxi Wang, Zihan Min, Zhongqi Ren, Zhihao Li, Tengxuan Liu, Shengxu Mu, Hanling Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28577 · open-access PDF
Large Language Model (LLM) Agenten können zunehmend komplexe Aufgaben bewältigen und lange Trajektorien von Beobachtungen und Aktionen navigieren. Wenn diese Trajektorien wachsen, werden Key-Value-Cache-I/O (KV) und Speicher die dominanten Kosten. Trajektorien können auch die maximale Kontextlänge des LLM überschreiten, was die Kontrolle über das aktive Cache-Wachstum erfordert. Vorherige Arbeiten verwenden Kontexttechnik, um die Cache-Größe zu reduzieren, indem sie die Geschichte trimmen oder zusammenfassen.
Machine translation (Meta M2M100); the English original follows.
Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage become the dominant cost. Trajectories can also exceed the LLM's maximum context length, requiring control over active cache growth. Prior work uses context engineering to reduce cache size by trimming or summarizing history. However, modifying the trajectory prefix invalidates subsequent cached states and triggers costly re-prefilling of retained context. Task accuracy can also suffer when too little
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28577, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange