List your company

Mathematical Reasoning on GSM8K (Accuracy, Accuracy degradation)

0.3Accuracy Degradation (Δ)GTD
0.041.7953.555.305Oct 9, 2025

Evaluation results

MethodLinks
GTDFailure Scenario=Single-agent failure2025.100.3—
GTDFailure Scenario=Noisy agent (50% err.)2025.101.4—
MaASFailure Scenario=Single-agent failure2025.101.8—
GTDFailure Scenario=Two-agent failure2025.102.1—
G-Des.Failure Scenario=Single-agent failure2025.102.1—
MaASFailure Scenario=Noisy agent (50% err.)2025.103.2—
G-Des.Failure Scenario=Noisy agent (50% err.)2025.103.9—
MaASFailure Scenario=Two-agent failure2025.105.6—
G-Des.Failure Scenario=Two-agent failure2025.106.8—
G-Des.Failure Scenario=No failure2025.10—92.09
GTDFailure Scenario=No failure2025.10—94.14
MaASFailure Scenario=No failure2025.10—92.3