{
  "id": 20369686,
  "title": "What Moves a LoCoMo Score? Memory Context, Answer Prompts and Judges",
  "url": "https://urgent.news/2026/11/14/what-moves-a-locomo-score-memory-context-answer-prompts-and-judges",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-14T06:41:22.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.19199v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "LoCoMo is a widely reported benchmark for long-term conversational memory, but published scores mix memory quality with choices of answer prompt, judge and baseline layout that are rarely reported together. We measure how much these choices move a score, and evaluate Becos, a team memory system for coding agents, as a black box under all of them: ten conversations (1,540 questions), two answer…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}