A prompt-shared hierarchical offline RL pipeline for LLM agents improves long-horizon task scores on ScienceWorld and ALFWorld over non-hierarchical baselines.
Exploration by random network distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
A prompt-shared hierarchical offline RL pipeline for LLM agents improves long-horizon task scores on ScienceWorld and ALFWorld over non-hierarchical baselines.