SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.
arXiv preprint arXiv:2408.10504 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Supplement Generation Training for Enhancing Agentic Task Performance
SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.