Unverified50% confidenceBenchmarkExact time

BranchOPD outperforms both Vanilla OPD and the more expensive Multi-Rollout OPD (n=7) on all evaluation benchmarks.

1

Sources

50%

Confidence

Long-term

Relevance

10/12/2026

First Seen

Sources

BranchOPD: Making On-Policy Distillation More Efficient with Branch Sampling

Related Entities

BranchOPDconcept Multi-Rollout OPDconcept

Related Claims

UnverifiedOn the ID/OOD average success rate on ALFWorld, BranchOPD improves over Vanilla OPD by 13.8 percentage points.59% similar UnverifiedAcross a total of 446 pairwise comparisons, CTD statistically significantly outperforms current state-of-the-art methods in 72.9% of cases.51% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/1001145

API

curl https://kongchang.com/api/v1/knowledge/claims/1001145

MCP

get_claim(id=1001145)