Sakana Fugu trains LLM orchestrators using fine-tuning, evolutionary algorithms, and RL to build query-adaptive multi-agent scaffolds, claiming SOTA results on benchmarks including SWE-Bench Pro and GPQA-Diamond.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RankGLU improves mean information coefficient on CSI300 from 0.0654 to 0.0727 by using a residual bottleneck gated linear unit for cross-sectional stock score formation.
citing papers explorer
-
Sakana Fugu Technical Report
Sakana Fugu trains LLM orchestrators using fine-tuning, evolutionary algorithms, and RL to build query-adaptive multi-agent scaffolds, claiming SOTA results on benchmarks including SWE-Bench Pro and GPQA-Diamond.
-
RankGLU: Residual Gated Score Formation for Cross-Sectional Stock Prediction
RankGLU improves mean information coefficient on CSI300 from 0.0654 to 0.0727 by using a residual bottleneck gated linear unit for cross-sectional stock score formation.