List your company

Multi-hop Question Answering on HotpotQA N=60 (test)

1Average Roundsfixed_k1
0.82.153.54.85Jun 25, 2026

Evaluation results

MethodLinks
fixed_k1Policy=fixed_k12026.061860.030.17—
shp (full)Policy=shp (full)2026.062.41290.0040.78—
oracle_isPolicy=oracle_is2026.062.731700.1153—
fixed_k3Policy=fixed_k32026.063530.0010.97—
entropy_onlyPolicy=entropy_only2026.063.92380.0040.81—
fixed_k6 (base)Policy=fixed_k62026.066————
critic_onlyPolicy=critic_only2026.06600——