@article{sridhar2025regent,
  title = {{REGENT}: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments},
  author = {Kaustubh Sridhar and Souradeep Dutta and Dinesh Jayaraman and Insup Lee},
  abstract = {Do generalist agents require large models pre-trained on massive amounts of data to rapidly adapt to new environments? We propose a novel approach to pre-train relatively small models and adapt them to unseen environments via in-context learning, without any finetuning. Our key idea is that retrieval offers a powerful bias for fast adaptation. Indeed, we demonstrate that even a simple retrieval-based 1-nearest neighbor agent offers a surprisingly strong baseline for today's state-of-the-art generalist agents. From this starting point, we construct a semi-parametric agent, REGENT, that trains a transformer-based policy on sequences of queries and retrieved neighbors. REGENT can generalize to unseen robotics and game-playing environments via retrieval augmentation and in-context learning, achieving this with up to 3x fewer parameters and up to an order-of-magnitude fewer pre-training datapoints, significantly outperforming today's state-of-the-art generalist agents.},
  journal = {ICLR},
  year = {2025},
  month = {Apr},
  pub_type = {conference},
  award = {Oral Presentation, 1.82% accept rate},
  url_pdf = {/publication/sridhar-2025-regent/sridhar-2025-regent.pdf},
  url_project = {https://kaustubhsridhar.github.io/regent-research/},
  url_code = {https://github.com/regent-research/regent},
  url_openreview = {https://openreview.net/forum?id=NxyfSW6mLK},
  url = {https://arxiv.org/abs/2412.04759},
  url_arxiv = {https://arxiv.org/abs/2412.04759},
}