TokenPilot: Cache-Efficient Context Management for LLM Agents

arXiv:2606.17016 · cs.CL, cs.AI, cs.LG, cs.MA · Submitted 2026-06-15 · Read on arXiv

cs.CL, cs.AI, cs.LG, cs.MA

Submitted: 2026-06-15

Updated: 2026-08-28

Comments: EMNLP 2026 Findings

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

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 9× in this paper · explained in 2 episodes
• Pruning — 7× in this paper · explained in 4 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Trace — 6× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Ablation — 3× in this paper · explained in 1 episode
• Abstraction — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• KV cache — 3× in this paper · explained in 3 episodes
• Sparsity — 3× in this paper · explained in 4 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Knowledge Graph — 2× in this paper · explained in 7 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Agent Architectures — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Agent Memory — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• KV cache reuse — 1× in this paper · explained in 2 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• LightMem: Lightweight and Efficient Memory-Augmented Generation
• AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
• LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
• EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
• Memory in the Age of AI Agents
• Compressing Code Context for LLM-based Issue Resolution
• Memory OS of AI Agent
• The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
• MemOS: A Memory OS for AI System
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
• Context as a Tool: Context Management for Long-Horizon SWE-Agents
• The Missing Memory Hierarchy: Demand Paging for LLM Context Windows
• A Survey of Context Engineering for Large Language Models
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• MemGPT: Towards LLMs as Operating Systems
• MemoBrain: Executive Memory as an Agentic Brain for Reasoning
• Zep: A Temporal Knowledge Graph Architecture for Agent Memory
• Scaling Long-Horizon LLM Agent via Context-Folding
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering