{
  "id": 16238,
  "url": "https://arxiv.org/abs/2608.01964",
  "title": "LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks",
  "summary": "Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to track and allowing incorrect self-assessments to propagate into later decisions. We reformulate long-horizon execution as a task-state management problem and propose LongHorizon-Ha",
  "authors": "Ziyu Ma, Hailang Huang, Shun Zou, Yong Wang, Shidong Yang, Yiming Hu",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-02T20:00:00.000Z",
  "fetched_at": "2026-08-05T05:10:44.550Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/16238",
  "original_url": "https://arxiv.org/abs/2608.01964",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}