{
  "id": 16911,
  "url": "https://arxiv.org/abs/2608.05141v1",
  "title": "OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling",
  "summary": "Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. Existing long-context corpora, however, are dominated by books, academic articles, and code repositories, which are finite resources and often scarce in long-distance dependencies. In this work, we introduce OctoLong, a context engineering pipeline that instruments an AST parser, a language server backend, and a package manager",
  "authors": "Indraneil Paul, Falko Helm, Goran Glavaš, Iryna Gurevych",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-05T17:58:15.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16911",
  "original_url": "https://arxiv.org/abs/2608.05141v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}