GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

Sarkar Snigdha Sarathi Das, Ryo Kamoi, Bo Pang, Yusen Zhang, Caiming Xiong +1 more
2/12/2026

No official code found. Best implementation: psunlpgroup/GreaTer (36 stars, last commit 2025-04-18).

Semantic Scholar

Code Implementations(1)

psunlpgroup/GreaTerCommunity74%

Source code for GreaTer ICLR 2025 - Gradient Over Reasoning makes Smaller Language Models Strong Prompt Optimizers

366Shell, PythonNov 11, 20241 years ago

Cite this paper

@article{das2026greater,
  title  = {GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers},
  author = {Sarkar Snigdha Sarathi Das and Ryo Kamoi and Bo Pang and Yusen Zhang and Caiming Xiong and Rui Zhang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:b54605ab6f7d5d5c326a99cff341843bdebb8b7d},
  journal = {ICLR 2025 2025}
}

Discussion