alphaXiv(@askalphaxiv):"Context Language Models" Most agents rely on an external harness to manage context. This paper instead lets the model directly rewrite its own context as a file, learning when to compress, delete, preserve, or reorganize information. At zero-shot, it gets 11.4% higher BrowseComp-Plus accuracy with 21.5% fewer FLOPs, and RL further improves the context-management policy.

2026.10.04 14:53

"Context Language Models" Most agents rely on an external harness to manage context. This paper instead lets the model directly rewrite its own context as a file, learning when to compress, delete, preserve, or reorganize information. At zero-shot, it gets 11.4% higher BrowseComp-Plus accuracy with 21.5% fewer FLOPs, and RL further improves the context-management policy.