{
  "id": 12966,
  "url": "https://arxiv.org/abs/2607.20064v1",
  "title": "PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning",
  "summary": "Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents. This gap is reflected in their limited performance on continual learning benchmarks such as ARC-AGI-3, especially when models are evaluated out of the box. Various agent harnesses have been proposed to close this gap, and each commits to a strategy for handling long sequences of observations, i.e., what information to save from the environment and how",
  "authors": "Alexis Fox, Junlin Wang, Paul Rosu, Bhuwan Dhingra",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-22T12:11:51.000Z",
  "fetched_at": "2026-07-23T05:10:49.458Z",
  "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/12966",
  "original_url": "https://arxiv.org/abs/2607.20064v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}