🐦 Twitter Post Details

Viewing enriched Twitter post

@dair_ai

// Graph Augmented Associative Memory for Agents // Long-term memory for agents is still an unsolved problem. Flat RAG loses structural relationships, and knowledge graphs miss conversational associations. New research proposes combining both through a hierarchical approach. GAAMA is a graph-augmented associative memory that constructs a concept-mediated hierarchical knowledge graph through episode preservation, LLM-based fact extraction, and higher-order reflection synthesis. It uses four node types connected by five edge types, with retrieval combining semantic search and graph-traversal ranking. On the LoCoMo-10 benchmark, GAAMA achieves 78.9% mean reward, outperforming HippoRAG and tuned RAG baselines. Multi-session agents need memory that captures both facts and their relationships across conversations. GAAMA demonstrates that graph-augmented retrieval consistently beats semantic-only methods, and that higher-order reflections, not just raw fact storage, are key to reliable recall. Paper: https://t.co/b9mWe4sN8c Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2039072251199549573/media_0.png",
      "filename": "media_0.png"
    },
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2039072251199549573/media_1.png",
      "filename": "media_1.png"
    }
  ],
  "processed_at": "2026-03-31T20:17:08.487793",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2039072251199549573",
  "url": "https://x.com/dair_ai/status/2039072251199549573",
  "twitterUrl": "https://twitter.com/dair_ai/status/2039072251199549573",
  "text": "// Graph Augmented Associative Memory for Agents //\n\nLong-term memory for agents is still an unsolved problem.\n\nFlat RAG loses structural relationships, and knowledge graphs miss conversational associations.\n\nNew research proposes combining both through a hierarchical approach.\n\nGAAMA is a graph-augmented associative memory that constructs a concept-mediated hierarchical knowledge graph through episode preservation, LLM-based fact extraction, and higher-order reflection synthesis.\n\nIt uses four node types connected by five edge types, with retrieval combining semantic search and graph-traversal ranking.\n\nOn the LoCoMo-10 benchmark, GAAMA achieves 78.9% mean reward, outperforming HippoRAG and tuned RAG baselines.\n\nMulti-session agents need memory that captures both facts and their relationships across conversations.\n\nGAAMA demonstrates that graph-augmented retrieval consistently beats semantic-only methods, and that higher-order reflections, not just raw fact storage, are key to reliable recall.\n\nPaper: https://t.co/b9mWe4sN8c\n\nLearn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c",
  "source": "Twitter for iPhone",
  "retweetCount": 1,
  "replyCount": 1,
  "likeCount": 5,
  "quoteCount": 0,
  "viewCount": 246,
  "createdAt": "Tue Mar 31 20:08:03 +0000 2026",
  "lang": "en",
  "bookmarkCount": 4,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2039072251199549573",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "dair_ai",
    "url": "https://x.com/dair_ai",
    "twitterUrl": "https://twitter.com/dair_ai",
    "id": "889050642903293953",
    "name": "DAIR.AI",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1643277398522187778/31dedbLo_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/889050642903293953/1773242460",
    "description": "",
    "location": "",
    "followers": 93810,
    "following": 1,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sun Jul 23 09:12:45 +0000 2017",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 4295,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 183,
    "statusesCount": 3054,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2038968068706390117"
    ],
    "profile_bio": {
      "description": "Democratizing AI research, education, and technologies. New AI learning portal: https://t.co/LRnpZN7L4c",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://academy.dair.ai/",
              "indices": [
                80,
                103
              ],
              "url": "https://t.co/LRnpZN7L4c"
            }
          ],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/lkqPZtMU5s"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/Nomym9aDJD",
        "expanded_url": "https://twitter.com/dair_ai/status/2039072251199549573/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2039072247974162432",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2039072247974162432",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxMPWfz23AACgACHEw9aLQa8IUAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHEw9Z/PbcAAKAAIcTD1otBrwhQAA",
            "media_key": "3_2039072247974162432"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HEw9Z_PbcAAvRWd.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 895,
              "w": 1598,
              "x": 0,
              "y": 0
            },
            {
              "h": 1598,
              "w": 1598,
              "x": 0,
              "y": 0
            },
            {
              "h": 1724,
              "w": 1512,
              "x": 0,
              "y": 0
            },
            {
              "h": 1724,
              "w": 862,
              "x": 300,
              "y": 0
            },
            {
              "h": 1724,
              "w": 1598,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1724,
          "width": 1598
        },
        "sizes": {
          "large": {
            "h": 1724,
            "w": 1598
          }
        },
        "type": "photo",
        "url": "https://t.co/Nomym9aDJD"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2603.27910",
        "expanded_url": "https://arxiv.org/abs/2603.27910",
        "indices": [
          1018,
          1041
        ],
        "url": "https://t.co/b9mWe4sN8c"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          1094,
          1117
        ],
        "url": "https://t.co/LRnpZN7L4c"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}