Self-Discover
Self-Discover has the model compose a task-specific reasoning structure by selecting, adapting, and combining general reasoning modules, such as critical thinking or step-by-step analysis, before solving instances of the task.
Description
The structure is discovered once per task and then reused, so it costs far fewer inference calls than sampling-heavy methods like self-consistency.
Sources
- Zhou et al. (2024). Self-Discover: Large Language Models Self-Compose Reasoning Structures.
Cite this entry
Protologue. (2026). Self-Discover. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0037). https://protologue.com/t/self-discover/
BibTeX
@misc{protologue_self_discover,
title = {Self-Discover},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0037},
url = {https://protologue.com/t/self-discover/}
}