Appending freshly sampled Gaussian noise vectors to LLM inputs reproduces much of the benefit of trained soft prompts, pointing to injection-induced trajectory diversity as the key mechanism.
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
Appending freshly sampled Gaussian noise vectors to LLM inputs reproduces much of the benefit of trained soft prompts, pointing to injection-induced trajectory diversity as the key mechanism.