SSRL, a training pipeline that uses an LLM's own repeated sampling as a search environment for RL, improves question answering without external tools and transfers to real search engines.
Worldcoder, a model-based llm agent: Building world models by writing code and interacting with the environment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SSRL: Self-Search Reinforcement Learning
SSRL, a training pipeline that uses an LLM's own repeated sampling as a search environment for RL, improves question answering without external tools and transfers to real search engines.