Coding agents navigating a file system outperform SOTA long-context LLMs and RAG systems on massive datasets.
March 24, 2026
Original Paper
Coding Agents are Effective Long-Context Processors
arXiv · 2603.20432
The Takeaway
Instead of scaling context windows or using vector search, this approach treats long-context processing as a navigation and tool-use task for agents. It achieves a 17.3% improvement over SOTA by externalizing memory into an interpretable file system structure.
From the abstract
Large Language Models (LLMs) have demonstrated remarkable progress in scaling to access massive contexts. However, the access is via the latent and uninterpretable attention mechanisms, and LLMs fail to effective process long context, exhibiting significant performance degradation as context length increases. In this work, we study whether long-context processing can be externalized from latent attention into explicit, executable interactions, by allowing coding agents to organize text in file s