🐦 Twitter Post Details

Viewing enriched Twitter post

@dair_ai

RT @omarsar0: New research from Intuit AI Research. Agent performance depends on more than just the agent. It also depends on the quality of the tool descriptions it reads. However, tool interfaces are still written for humans, not LLMs. As the number of candidate tools grows, poor descriptions become a real bottleneck for tool selection and parameter generation. As Karpathy has suggested, let's build for AI Agents. This new research introduces Trace-Free+, a curriculum learning framework that teaches models to rewrite tool descriptions into versions that are more effective for LLM agents. The key idea: during training, the model learns from execution traces showing which tool descriptions lead to successful usage. Then, through curriculum learning, it progressively reduces reliance on traces, so at inference time, it can improve tool descriptions for completely unseen tools without any execution history. On StableToolBench and RestBench, the approach shows consistent gains on unseen tools, strong cross-domain generalization, and robustness as candidate tool sets scale beyond 100. Instead of only fine-tuning the agent, optimizing the tool interface itself is a practical and underexplored lever for improving agent reliability. Paper: https://t.co/BeVigJNGYY Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

📊 Media Metadata

{
  "score": 0.36,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.06000000000000001,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-03-01T12:15:47.997882",
  "import_source": "api_import",
  "source_tagged_at": "2026-03-01T12:15:47.997895",
  "enriched": true,
  "enriched_at": "2026-03-01T12:15:47.997898"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2026677614962713015",
  "url": "https://x.com/dair_ai/status/2026677614962713015",
  "twitterUrl": "https://twitter.com/dair_ai/status/2026677614962713015",
  "text": "RT @omarsar0: New research from Intuit AI Research.\n\nAgent performance depends on more than just the agent. It also depends on the quality…",
  "source": "Twitter for iPhone",
  "retweetCount": 18,
  "replyCount": 17,
  "likeCount": 124,
  "quoteCount": 0,
  "viewCount": 10990,
  "createdAt": "Wed Feb 25 15:16:11 +0000 2026",
  "lang": "en",
  "bookmarkCount": 125,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2026677614962713015",
  "displayTextRange": [
    0,
    139
  ],
  "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/889050642903293953/1742055232",
    "description": "",
    "location": "",
    "followers": 90586,
    "following": 1,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sun Jul 23 09:12:45 +0000 2017",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 4185,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 161,
    "statusesCount": 2963,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2028094132090966088"
    ],
    "profile_bio": {
      "description": "Democratizing AI research, education, and technologies.",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/lkqPZtMmfU"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [],
    "user_mentions": [
      {
        "id_str": "3448284313",
        "indices": [
          3,
          12
        ],
        "name": "elvis",
        "screen_name": "omarsar0"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": {
    "type": "tweet",
    "id": "2026676835539628465",
    "url": "https://x.com/omarsar0/status/2026676835539628465",
    "twitterUrl": "https://twitter.com/omarsar0/status/2026676835539628465",
    "text": "New research from Intuit AI Research.\n\nAgent performance depends on more than just the agent. It also depends on the quality of the tool descriptions it reads.\n\nHowever, tool interfaces are still written for humans, not LLMs. As the number of candidate tools grows, poor descriptions become a real bottleneck for tool selection and parameter generation.\n\nAs Karpathy has suggested, let's build for AI Agents.\n\nThis new research introduces Trace-Free+, a curriculum learning framework that teaches models to rewrite tool descriptions into versions that are more effective for LLM agents.\n\nThe key idea: during training, the model learns from execution traces showing which tool descriptions lead to successful usage. Then, through curriculum learning, it progressively reduces reliance on traces, so at inference time, it can improve tool descriptions for completely unseen tools without any execution history.\n\nOn StableToolBench and RestBench, the approach shows consistent gains on unseen tools, strong cross-domain generalization, and robustness as candidate tool sets scale beyond 100.\n\nInstead of only fine-tuning the agent, optimizing the tool interface itself is a practical and underexplored lever for improving agent reliability.\n\nPaper: https://t.co/BeVigJNGYY\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
    "source": "Twitter for iPhone",
    "retweetCount": 18,
    "replyCount": 17,
    "likeCount": 124,
    "quoteCount": 0,
    "viewCount": 10990,
    "createdAt": "Wed Feb 25 15:13:06 +0000 2026",
    "lang": "en",
    "bookmarkCount": 125,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2026676835539628465",
    "displayTextRange": [
      0,
      270
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "omarsar0",
      "url": "https://x.com/omarsar0",
      "twitterUrl": "https://twitter.com/omarsar0",
      "id": "3448284313",
      "name": "elvis",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
      "description": "",
      "location": "DAIR.AI Academy",
      "followers": 291571,
      "following": 776,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 34909,
      "hasCustomTimelines": true,
      "isTranslator": true,
      "mediaCount": 4525,
      "statusesCount": 17379,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2028103978190590118"
      ],
      "profile_bio": {
        "description": "Building @dair_ai • Prev: Meta AI, Elastic, PhD • New AI learning portal: https://t.co/1e8RZKs4uX",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [
              {
                "display_url": "academy.dair.ai",
                "expanded_url": "https://academy.dair.ai/",
                "indices": [
                  74,
                  97
                ],
                "url": "https://t.co/1e8RZKs4uX"
              }
            ],
            "user_mentions": [
              {
                "id_str": "0",
                "indices": [
                  9,
                  17
                ],
                "name": "",
                "screen_name": "dair_ai"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "dair.ai",
                "expanded_url": "https://www.dair.ai/",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/XQto5ypSIk"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "display_url": "pic.twitter.com/i0xR0qh3Z3",
          "expanded_url": "https://twitter.com/omarsar0/status/2026676835539628465/photo/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "features": {
            "large": {
              "faces": []
            },
            "orig": {
              "faces": []
            }
          },
          "id_str": "2026676831701946368",
          "indices": [
            271,
            294
          ],
          "media_key": "3_2026676831701946368",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwgM9c0G9AACgACHCAz2BjaMbEAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABHCAz1zQb0AAKAAIcIDPYGNoxsQAA",
              "media_key": "3_2026676831701946368"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HCAz1zQb0AANza2.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 841,
                "w": 1502,
                "x": 0,
                "y": 0
              },
              {
                "h": 1502,
                "w": 1502,
                "x": 0,
                "y": 0
              },
              {
                "h": 1712,
                "w": 1502,
                "x": 0,
                "y": 0
              },
              {
                "h": 1784,
                "w": 892,
                "x": 490,
                "y": 0
              },
              {
                "h": 1784,
                "w": 1502,
                "x": 0,
                "y": 0
              }
            ],
            "height": 1784,
            "width": 1502
          },
          "sizes": {
            "large": {
              "h": 1784,
              "w": 1502
            }
          },
          "type": "photo",
          "url": "https://t.co/i0xR0qh3Z3"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [
        {
          "display_url": "arxiv.org/abs/2602.20426",
          "expanded_url": "https://arxiv.org/abs/2602.20426",
          "indices": [
            1247,
            1270
          ],
          "url": "https://t.co/BeVigJNGYY"
        },
        {
          "display_url": "academy.dair.ai",
          "expanded_url": "https://academy.dair.ai/",
          "indices": [
            1323,
            1346
          ],
          "url": "https://t.co/1e8RZKs4uX"
        }
      ],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "isLimitedReply": false,
  "article": null
}