Agents

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

Single source1 source14 Oct 2026

arXiv:2608.05141v2 Announce Type: replace Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2608.05141

← Back to all developments · Signals are a development reported by more than one source. See the methodology.