SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
Toolformer: Language models can teach themselves to use tools
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
ReSearch trains LLMs via RL to integrate search operations into reasoning steps, achieving strong generalization across benchmarks and eliciting reflection and self-correction without supervised reasoning data.
citing papers explorer
-
SOD: Step-wise On-policy Distillation for Small Language Model Agents
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
-
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
ReSearch trains LLMs via RL to integrate search operations into reasoning steps, achieving strong generalization across benchmarks and eliciting reflection and self-correction without supervised reasoning data.