🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

This new paper extends in-context learning through high-level automated reasoning. It achieves state-of-the-art accuracy (79.6%) on the MATH benchmark with Qwen2.5-7B-Instruct, surpassing GPT-4o (76.6%) and Claude 3.5 (71.1%). Rather than focusing on manually creating high-quality demonstrations, it shifts the focus to abstract thinking patterns. It introduces five atomic reasoning actions to construct chain-structured patterns. Then it uses Monte Carlo Tree Search to explore reasoning paths and construct though cards to guide inference. There is also a dynamic component that can match problems with the appropriate thought cards.

Media 1
View on Twitter

📊 Media Metadata

{
  "score": 1.0,
  "scored_at": "2025-08-09T13:46:07.555116",
  "import_source": "network_archive_import",
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1862131336653533584/media_0.png?",
      "filename": "media_0.png"
    },
    {
      "media_url": "https://pbs.twimg.com/media/GdeelK0WgAAGBpz.png",
      "type": "photo"
    }
  ],
  "reprocessed_at": "2025-08-12T15:26:55.990577",
  "reprocessed_reason": "missing_media_array",
  "original_structure": "had_both"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2015-09-04T12:59:26.000Z",
    "default_profile_image": false,
    "description": "Building with AI Agents @dair_ai • Prev: Meta AI, Elastic, Galactica LLM, PhD • I also teach how to build with LLMs, RAG & AI Agents ⬇️",
    "fast_followers_count": 0,
    "favourites_count": 27931,
    "followers_count": 216712,
    "friends_count": 532,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 3689,
    "location": "",
    "media_count": 2656,
    "name": "elvis",
    "normal_followers_count": 216712,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "screen_name": "omarsar0",
    "statuses_count": 12439,
    "translator_type": "regular",
    "url": "https://t.co/JBU5beHQNs",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "3448284313"
  },
  "id": "1862131336653533584",
  "conversation_id": "1862131336653533584",
  "full_text": "This new paper extends in-context learning through high-level automated reasoning.\n\nIt achieves state-of-the-art accuracy (79.6%) on the MATH benchmark with Qwen2.5-7B-Instruct, surpassing GPT-4o (76.6%) and Claude 3.5 (71.1%).\n\nRather than focusing on manually creating high-quality demonstrations, it shifts the focus to abstract thinking patterns.\n\nIt introduces five atomic reasoning actions to construct chain-structured patterns. Then it uses Monte Carlo Tree Search to explore reasoning paths and construct though cards to guide inference.\n\nThere is also a dynamic component that can match problems with the appropriate thought cards.",
  "reply_count": 8,
  "retweet_count": 104,
  "favorite_count": 427,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GdeelK0WgAAGBpz.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/omarsar0/status/1862131336653533584",
  "created_at": "2024-11-28T13:48:02.000Z",
  "#sort_index": "1862131336653533584",
  "view_count": 58359,
  "quote_count": 3,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/omarsar0/status/1862131336653533584"
}