CUDAnalyst enables generation-level attribution of heterogeneous feedback effects on planning in self-evolving LLM agents for CUDA kernel generation via controlled trajectory freezing and injection experiments.
ISBN 9781450312851
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
CUDAnalyst enables generation-level attribution of heterogeneous feedback effects on planning in self-evolving LLM agents for CUDA kernel generation via controlled trajectory freezing and injection experiments.