InstructRAG combines instruction paths from a graph via reinforcement learning and meta-learned selection, reporting relative gains of 2 to 25 percent over its chosen baselines across four LLM planning benchmarks.
Title resolution pending
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
-
InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning
InstructRAG combines instruction paths from a graph via reinforcement learning and meta-learned selection, reporting relative gains of 2 to 25 percent over its chosen baselines across four LLM planning benchmarks.