Using Introspective Reasoning to Refine Indexing

Introspective reasoning about a system's own reasoning processes can form the basis for learning to re ne those reasoning processes. The ROBBIE system uses introspective reasoning to monitor the retrieval process of a case-based planner to detect retrieval of inappropriate cases. When retrieval problems are detected, the source of the problems is explained and the explanations are used to determine new indices to use during future case retrieval. The goal of ROBBIE's learning is to increase its ability to focus retrieval on relevant cases, with the aim of simultaneously decreasing the number of candidates to consider and increasing the likelihood that the system will be able to successfully adapt the retrieved cases to t the current situation. We evaluate the benets of the approach in light of empirical results examining the e ects of index learning in the ROBBIE system.