VPO modifies the GRPO advantage estimator to train LLMs for diversity across vector reward trade-offs, matching or exceeding scalar RL baselines on test-time search with larger gains at higher search budgets.
Find- ing evidence for reasoning step 1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
VPO modifies the GRPO advantage estimator to train LLMs for diversity across vector reward trade-offs, matching or exceeding scalar RL baselines on test-time search with larger gains at higher search budgets.