List your company

Question Answering on HotpotQA (Perf, Cost, Reward)

0.4335PerfRouteLLM
0.3396920.3640460.38840.412754Jan 9, 2026

Evaluation results

MethodLinks
RouteLLMalpha=0.8, beta=0.22026.010.43350.21110.3046
IRT-Routeralpha=0.8, beta=0.22026.010.42990.13770.3164
HAPSalpha=0.8, beta=0.22026.010.41940.08860.3178
HAPSalpha=0.2, beta=0.82026.010.41810.08610.0148
HAPSalpha=0.5, beta=0.52026.010.37090.08570.1426
All Strongalpha=0.8, beta=0.22026.010.36970.33620.2285
All Strongalpha=0.5, beta=0.52026.010.36970.33620.0168
All Strongalpha=0.2, beta=0.82026.010.36970.3362-0.195
IRT-Routeralpha=0.5, beta=0.52026.010.36040.09210.1341
RouteLLMalpha=0.5, beta=0.52026.010.35580.09390.131
IRT-Routeralpha=0.2, beta=0.82026.010.35520.08810.0005
All Weakalpha=0.8, beta=0.22026.010.34580.09230.2582
All Weakalpha=0.5, beta=0.52026.010.34580.09230.1267
All Weakalpha=0.2, beta=0.82026.010.34580.0923-0.0047
RouteLLMalpha=0.2, beta=0.82026.010.34580.0923-0.0047
GraphRouteralpha=0.8, beta=0.22026.010.34580.09230.2582
GraphRouteralpha=0.5, beta=0.52026.010.34580.09230.1267
GraphRouteralpha=0.2, beta=0.82026.010.34580.0923-0.0047
Randomalpha=0.8, beta=0.22026.010.34330.2160.2314
Randomalpha=0.5, beta=0.52026.010.34330.2160.0636
Randomalpha=0.2, beta=0.82026.010.34330.216-0.1042