{
  "id": 6411,
  "url": "https://arxiv.org/abs/2604.02734v1",
  "title": "Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents",
  "summary": "Large language models (LLMs) have demonstrated strong potential in long-horizon decision-making tasks, such as embodied manipulation and web interaction. However, agents frequently struggle with endless trial-and-error loops or deviate from the main objective in complex environments. We attribute these failures to two fundamental errors: global Progress Drift and local Feasibility Violation. Existing methods typically attempt to address both issues simultaneously using a single paradigm. However",
  "authors": "Bin Wen, Ruoxuan Zhang, Yang Chen, Hongxia Xie, Lan-Zhe Guo",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-03T05:11:19.000Z",
  "fetched_at": "2026-07-14T16:32:28.610Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6411",
  "original_url": "https://arxiv.org/abs/2604.02734v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}