SeaEvo introduces a modular strategy-space layer that organizes LLM reasoning into first-class evolutionary state, delivering 20.6% average relative improvement on algorithm discovery and systems benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
SeaEvo introduces a modular strategy-space layer that organizes LLM reasoning into first-class evolutionary state, delivering 20.6% average relative improvement on algorithm discovery and systems benchmarks.