pith. machine review for the scientific record. sign in

Reinforcement learning with deep energy-based policies

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Process Reinforcement through Implicit Rewards

cs.LG · 2025-02-03 · conditional · novelty 6.0

PRIME enables online process reward model updates in LLM RL using implicit rewards from rollouts and outcome labels, yielding 15.1% average gains on reasoning benchmarks and surpassing a stronger instruct model with 10% of the data.

citing papers explorer

Showing 1 of 1 citing paper.

  • Process Reinforcement through Implicit Rewards cs.LG · 2025-02-03 · conditional · none · ref 15

    PRIME enables online process reward model updates in LLM RL using implicit rewards from rollouts and outcome labels, yielding 15.1% average gains on reasoning benchmarks and surpassing a stronger instruct model with 10% of the data.