MicroEvo couples LLM-driven evolutionary operators with a Pareto-aware MCTS and knowledge memory to achieve state-of-the-art sample efficiency in microarchitecture design space exploration.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
MicroEvo couples LLM-driven evolutionary operators with a Pareto-aware MCTS and knowledge memory to achieve state-of-the-art sample efficiency in microarchitecture design space exploration.