Spreadsheet Data Agent · v0.1.1

Code | Demo | Paper | Spreadsheet-RL Model

Send instructions and optional file context to Spreadsheet-RL-4B. This first inference surface implements the prompt-and-file entry point from the agent diagram.

Uses the original inference workflow: uploaded files are converted to plain data context and sent to the model with the prompt.

RL data input

System prompt

User prompt

Optional file context

Spreadsheet-RL-4B quantization

Static GGUF quants published by mradermacher; Q4_K_M is the reference recommendation.

Agent response

Generated text

Citation

If you use Spreadsheet-RL-4B, please cite the model's paper:

@misc{chi2026spreadsheetrl,
  title         = {Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning},
  author        = {Banghao Chi and Yining Xie and Mingyuan Wu and Jingcheng Yang and Jize Jiang and Zhaoheng Li and Shengyi Qian and Minjia Zhang and Klara Nahrstedt and Rui Hou and Xiangjun Fan and Hanchao Yu},
  year          = {2026},
  eprint        = {2605.22642},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
  doi           = {10.48550/arXiv.2605.22642},
  url           = {https://arxiv.org/abs/2605.22642}
}

Citation from the Spreadsheet-RL-4B model card.