A reinforcement-learned question-answering agent, IKEA, uses a reward favoring correct answers with fewer searches and a balanced easy/hard training set to cut retrieval frequency while keeping or improving accuracy.
Understand- ing the interplay between parametric and contextual knowledge for large language models, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
A reinforcement-learned question-answering agent, IKEA, uses a reward favoring correct answers with fewer searches and a balanced easy/hard training set to cut retrieval frequency while keeping or improving accuracy.