LHRL-VGR, a two-stage RL method with variance-based reward routing, lets a Qwen2.5-7B agent beat GPT-4o by about 7% on SOTOPIA goal completion.
Social foundations of thought and action
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding
LHRL-VGR, a two-stage RL method with variance-based reward routing, lets a Qwen2.5-7B agent beat GPT-4o by about 7% on SOTOPIA goal completion.