{
  "id": 15757923,
  "title": "ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model",
  "url": "https://urgent.news/2026/10/20/altk-evolve-how-learned-memory-tops-the-2-bench-leaderboard-on",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-20T15:19:48.000Z",
  "source": {
    "name": "Hugging Face",
    "slug": "hugging-face",
    "url": "https://huggingface.co/blog/ibm-research/altk-evolve-bc"
  },
  "original_language": "en",
  "account": "ALTK-Evolve, a customer service agent, has recently outperformed retail competitors on the τ²-bench benchmark by utilizing GPT-4.1 without updating model weights. This non-reasoning model achieved a Pass^4 of 67.5% across four independent attempts on tasks within the retail benchmark. The agent operates using GPT-4.1's stock ReAct scaffold with learned guidelines appended to its system prompt. ALTK-Evolve extracts these guidelines from the agent's training-task attempts and incorporates them into the agent's prompt for subsequent conversations, thereby improving its performance without the need for additional weight updates or human annotation.",
  "summary": null,
  "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."
}