Five dimensions of reasoning in the wild
This addresses the problem of improving reasoning systems for AI agents, but it is incremental as it builds on existing concepts without presenting concrete results.
The paper tackles the problem of reasoning failing when isolated from agent needs and world context, proposing that a new data structure incorporating perceptual knowledge and anticipatory action is needed to address these issues.
Reasoning does not work well when done in isolation from its significance, both to the needs and interests of an agent and with respect to the wider world. Moreover, those issues may best be handled with a new sort of data structure that goes beyond the knowledge base and incorporates aspects of perceptual knowledge and even more, in which a kind of anticipatory action may be key.