ERILS mixes length-controlled external rollouts from a stronger policy with on-policy rollouts and processes their rewards separately, substantially improving dLLM reinforcement learning on reasoning tasks.
Title resolution pending
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
-
Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models
ERILS mixes length-controlled external rollouts from a stronger policy with on-policy rollouts and processes their rewards separately, substantially improving dLLM reinforcement learning on reasoning tasks.