AMR uses difficulty-aware routing and uncertainty-guided aggregation across three experts plus a neural verifier to reach 75.28% accuracy on GSM8K without synthetic training data.
Gsm-plus: A comprehensive benchmark for evaluating the robustness of llms as mathematical problem solvers, 2024
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
-
Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation
AMR uses difficulty-aware routing and uncertainty-guided aggregation across three experts plus a neural verifier to reach 75.28% accuracy on GSM8K without synthetic training data.