ProcessThinker assigns step-level rewards in GRPO by sampling continuations from each step prefix and using empirical success rates, improving video reasoning benchmarks without training a separate PRM.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
ProcessThinker assigns step-level rewards in GRPO by sampling continuations from each step prefix and using empirical success rates, improving video reasoning benchmarks without training a separate PRM.