List your company

Evidence retrieval on tau-bench multi-burst-augmented cache

68Hit@2OSU-Mem + GF
-2.7215.643452.36Jun 19, 2026

Evaluation results

MethodLinks
OSU-Mem + GFBudget=B=5122026.066838.6
OSU-Mem (no novelty)Budget=B=5122026.066838.6
OSU-MemBudget=B=5122026.0667.638.4
Coverage-AwareBudget=B=5122026.0667.336.6
Flat + MMRBudget=B=5122026.0664.633.5
Flat VectorBudget=B=5122026.0657.431.8
OSU-Mem (disjoint)Budget=B=5122026.065228.8
OSU-Mem (sim only)Budget=B=5122026.0646.624.3
Disjoint HierarchyBudget=B=5122026.0646.527.1
OSU-MemBudget=B=2562026.0643.524.1
OSU-Mem + GFBudget=B=2562026.0643.524.1
OSU-Mem (no novelty)Budget=B=2562026.0641.923.3
OSU-Mem (disjoint)Budget=B=2562026.0638.720.9
Periodic SummaryBudget=B=5122026.0634.721.9
Flat + MMRBudget=B=2562026.0634.720.1
Coverage-AwareBudget=B=2562026.0633.320.1
Flat VectorBudget=B=2562026.0632.820.3
Tree AbstractionBudget=B=5122026.0631.620.3
OSU-Mem (sim only)Budget=B=2562026.0628.515.7
Disjoint HierarchyBudget=B=2562026.0628.118
OSU-MemBudget=B=1282026.062514.5
OSU-Mem + GFBudget=B=1282026.062514.5
OSU-Mem (no novelty)Budget=B=1282026.062514.5
Tree AbstractionBudget=B=2562026.0619.313.3
Periodic SummaryBudget=B=2562026.0618.812.7
Disjoint HierarchyBudget=B=1282026.0618.112.3
Flat + MMRBudget=B=1282026.0617.213.4
Coverage-AwareBudget=B=1282026.0617.113.6
Budget-Trunc ReplayBudget=B=5122026.0616.317.8
Sliding WindowBudget=B=5122026.0616.117.7
OSU-Mem (disjoint)Budget=B=1282026.06159.3
OSU-Mem (sim only)Budget=B=1282026.0614.58.6
Flat VectorBudget=B=1282026.0614.112.2
Tree AbstractionBudget=B=1282026.061312.3
OSU-MemBudget=B=642026.0612.58.5
OSU-Mem + GFBudget=B=642026.0612.58.5
OSU-Mem (no novelty)Budget=B=642026.0612.58.5
OSU-Mem (disjoint)Budget=B=642026.0610.96.1
Disjoint HierarchyBudget=B=642026.069.98
Budget-Trunc ReplayBudget=B=2562026.068.19.1
Tree AbstractionBudget=B=642026.068.18.6
Sliding WindowBudget=B=2562026.067.99
OSU-Mem (sim only)Budget=B=642026.066.34.5
Flat VectorBudget=B=642026.065.17.6
Flat + MMRBudget=B=642026.063.77.9
Coverage-AwareBudget=B=642026.063.27.6
Periodic SummaryBudget=B=1282026.062.65.3
Budget-Trunc ReplayBudget=B=1282026.060.54.9
Budget-Trunc ReplayBudget=B=642026.060.33.5
Periodic SummaryBudget=B=642026.060.33.4
Sliding WindowBudget=B=642026.0602.6
Sliding WindowBudget=B=1282026.0604.4