# TokenPilot: Cache-Efficient Context Management for LLM Agents

arXiv: https://arxiv.org/abs/2606.17016 · HTML: https://mlsanity.com/paper/2606.17016/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 28 of 28)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [AgentFold: Long-Horizon Web Agents with Proactive Context Management](https://mlsanity.com/paper/2510.24699/) (2025)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning](https://mlsanity.com/paper/2601.02163/) (2026)
- [Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality](https://mlsanity.com/paper/2505.18227/) (2025)
- [Context as a Tool: Context Management for Long-Horizon SWE-Agents](https://mlsanity.com/paper/2512.22087/) (2025)
- [LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation](https://mlsanity.com/paper/2510.04851/) (2025)
- [KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems](https://mlsanity.com/paper/2510.12872/) (2025)
- [RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory](https://mlsanity.com/paper/2508.04903/) (2025)
- [StructMem: Structured Memory for Long-Horizon Behavior in LLMs](https://mlsanity.com/paper/2604.21748/) (2026)
- [ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents](https://mlsanity.com/paper/2604.01664/) (2026)
- [StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management](https://mlsanity.com/paper/2601.05890/) (2026)
- [MemoBrain: Executive Memory as an Agentic Brain for Reasoning](https://mlsanity.com/paper/2601.08079/) (2026)
- [Compressing Code Context for LLM-based Issue Resolution](https://mlsanity.com/paper/2603.28119/) (2026)
- [AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents](https://mlsanity.com/paper/2603.27490/) (2026)
- [The Missing Memory Hierarchy: Demand Paging for LLM Context Windows](https://mlsanity.com/paper/2603.09023/) (2026)
- [Rethinking Memory as Continuously Evolving Connectivity](https://mlsanity.com/paper/2605.28773/) (2026)

## Built on by (most cited first, 3 of 3)

- [LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception](https://mlsanity.com/paper/2606.30005/) (2026)
- [Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents](https://mlsanity.com/paper/2609.32961/) (2026)
- [CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents](https://mlsanity.com/paper/2609.37012/) (2026)

## Abstract (arXiv)

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 https://github.com/zjunlp/RSI.