FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
DuST self-trains LLMs for code generation by ranking their own test-time samples via sandbox execution and applying GRPO, improving judgment by +6.2 NDCG and single-sample pass@1 by +3.1 on LiveCodeBench.
citing papers explorer
-
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
-
Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling
DuST self-trains LLMs for code generation by ranking their own test-time samples via sandbox execution and applying GRPO, improving judgment by +6.2 NDCG and single-sample pass@1 by +3.1 on LiveCodeBench.
- Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning