GR2 applies mid-training on semantic IDs, reasoning distillation, RL with conditional verifiable rewards, and a context compressor to re-ranking in industrial recsys, reporting +18.7% R@1 over baselines.
Strategic chain-of-thought: Guiding accurate reasoning in llms through strategy elicitation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
URSA is a modular agent ecosystem that uses LLMs and scientific tools to accelerate research tasks of varying complexity.
citing papers explorer
-
GR2 Technical Report
GR2 applies mid-training on semantic IDs, reasoning distillation, RL with conditional verifiable rewards, and a context compressor to re-ranking in industrial recsys, reporting +18.7% R@1 over baselines.
-
URSA: The Universal Research and Scientific Agent
URSA is a modular agent ecosystem that uses LLMs and scientific tools to accelerate research tasks of varying complexity.