# Track new AI agent, tool-use and RAG research papers

**Use case:** 

Ranks the last 3 days of arXiv cs.CL/cs.AI papers and Hugging Face daily papers about agents, tool use and retrieval, plus the top trending open models on Hugging Face. Each row has title, authors, links, upvotes and a relevance score.

## Input

```json
{
  "sources": [
    "arxiv",
    "hfDailyPapers",
    "hfTrendingModels"
  ],
  "arxivCategories": [
    "cs.CL",
    "cs.AI"
  ],
  "keywords": [
    "agent",
    "tool use",
    "retrieval"
  ],
  "daysBack": 3,
  "maxPapers": 20,
  "rankBy": "radarScore",
  "maxArxivScan": 200,
  "minUpvotes": 0,
  "onlyWithCode": false,
  "modelTasks": [
    "text-generation"
  ],
  "maxModels": 5,
  "onlyNew": false,
  "llmEnrichment": false
}
```

## Output

```json
{
  "rank": {
    "label": "Rank"
  },
  "radarScore": {
    "label": "Radar score"
  },
  "title": {
    "label": "Title"
  },
  "published": {
    "label": "Published"
  },
  "hfUpvotes": {
    "label": "Hf upvotes"
  },
  "githubStars": {
    "label": "Github stars"
  },
  "githubRepo": {
    "label": "Github repo",
    "format": "link"
  },
  "primaryCategory": {
    "label": "Primary category"
  },
  "matchedKeywords": {
    "label": "Matched keywords"
  },
  "absUrl": {
    "label": "Abs url",
    "format": "link"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The AI Research Radar: arXiv + Hugging Face Papers Actor is ready to run with the inputs already set for "Track new AI agent, tool-use and RAG research papers". [Sign up or log in](https://console.apify.com/create-task-from-example/LN74EcxnlOXxWRtUS) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Track new AI agent, tool-use and RAG research papers" task

The AI Research Radar: arXiv + Hugging Face Papers Actor will start running based on the input automatically. You can also change all the input fields, like sources, arxiv categories, and more, to match your specific use case.

### 3. Receive the "Track new AI agent, tool-use and RAG research papers" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as rank, radar score, title, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Track new AI agent, tool-use and RAG research papers" task via API](https://apify.com/tendoyo/ai-research-radar.md).

## About this Actor

This example demonstrates how to use [AI Research Radar: arXiv + Hugging Face Papers](https://apify.com/tendoyo/ai-research-radar.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/tendoyo/ai-research-radar.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/tendoyo/ai-research-radar.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).