Pith. sign in

Emergent world representations: Exploring a sequence model trained on a synthetic task

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

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

SSRL: Self-Search Reinforcement Learning

cs.CL · 2025-08-14 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • SSRL: Self-Search Reinforcement Learning cs.CL · 2025-08-14 · unverdicted · none · ref 26

    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.