#context management
4 papers · 1 filter
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
Binyan Xu, Haitao Li, Kehuan Zhang
The paper demonstrates that large language model agents can better manage their working memory when given an interface that reveals the size, age, and usage of each memory block, i…
ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
Zijun Xie, Binbin Zheng, Enlei Gong +7
The paper introduces ECHO, a framework that compresses each interaction turn of a language agent into indexed memory records and selectively reconstructs context for decision makin…
Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search
Howard Yen, Yoonsang Lee, Ashwin Paranjape +5
The paper introduces SLIM, a lightweight framework that separates search and browsing tools and periodically summarizes information to overcome context limits in long-horizon web‑a…
A hierarchical memory architecture overcomes context limits in long-horizon multi-agent computational modeling
Shivendra G. Tewari, Holly Kimko
The paper introduces Ensemble QSP, a multi‑agent framework with a three‑layer hierarchical memory that keeps context size bounded, enabling long‑horizon autonomous modeling of phar…