cs.AINov 19, 2026

Context as a Resource

Authors: Xufei Tian, Han Hu, Wenli Du

Organizations: East China University of Science and Technology, Shanghai, China

Abstract

Managing concurrent tasks across separate agent sessions quickly exhausts human attention, motivating always-on personal agents behind a single continuous interface. Yet when every context shares identical frozen backbone weights, funneling interleaved dialogues and external events into one linear session induces cross-topic constraint bleed and head-of-line stalling. Conversely, router-ticket hierarchies incur lossy prose handoffs, heavy routing overhead, and blind merges - collapsing true-conflict repository merges to a 33.3% three-run mean despite high isolated branch passes. Rather than scheduling anthropomorphic roles, we introduce ClonAct, a routerless architecture that virtualizes context blocks directly through a pluggable single-pass non-generative Context MMU, in-place Context Cells, a footprint-aware Synaptic Bus with an isolated trial merge gate, and a wave-flushed Shared Trunk. Across three programmatic multi-stream benchmarks and three model families, our portable trial merge gate lifts true-conflict merges to 63.3%, while ClonAct's routerless virtualization attains this ceiling with 45.9% fewer prompt tokens and prevents compact-model router collapse. Under continuous surge streams, ClonAct matches top completion (95.0%) with the lowest median wait and zero timed-out status checks.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Context Language Models

    Sep 29, 2026Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin +10Memory-Augmented Language ModelsLLM Context Management

  2. RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory

    Aug 6, 2025Jun Liu, Zhenglun Kong, Changdi Yang +12LLM Context ManagementMulti-Agent LLM Systems

  3. CTXAgent - Self-Controlled Context Management of LLM Agents

    Oct 25, 2026Matthias Busch, Marius Tacke, Roland C. Aydin +2LLM Context ManagementContext Compaction for LLM Agents