OPPO derives token-level advantages for LLM RL via Bayesian recursion on oracle signals, recovering prior distillation methods as a special case and showing gains on math and code benchmarks.
Towards understanding the optimization landscape of grpo and its variants
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
OPPO derives token-level advantages for LLM RL via Bayesian recursion on oracle signals, recovering prior distillation methods as a special case and showing gains on math and code benchmarks.