TokenPilot: Cache-Efficient Context Management for LLM Agents

[2606.17016] TokenPilot: Cache-Efficient Context Management for LLM Agents Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2606.17016 (cs) [Submitted on 15 Jun 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: TokenPilot: Cache-Efficient Context Management for LLM Agents Authors: Buqiang Xu , Zirui Xue , Dianmou Chen , Chenyang Fu , Chiyu Wu , Caiying Huang , Chen Jiang , Jizhan Fang , Xinle Deng , Yijun Chen , Yunzhi Yao , Xuehai Wang , Jin Shang , Gong Yu , Ningyu Zhang View PDF HTML (experimental) Abstract: As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightRSI at this https URL . Comments: EMNLP 2026 Findings Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA) Cite as: arXiv:2606.17016 [cs.CL] (or arXiv:2606.17016v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.17016 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ningyu Zhang [ view email ] [v1] Mon, 15 Jun 2026 17:46:50 UTC (1,641 KB) [v2] Fri, 28 Aug 2026 01:44:50 UTC (1,646 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-06 Change to browse by: cs cs.AI cs.LG cs.MA References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• TokenPilot: Cache-Efficient Context Management for LLM Agents#682723
• TokenPilot: Cache-Efficient Context Management for LLM Agents#280189
• AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents#229449
• LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle#346575
• SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment#13975