<?xml version="1.0" standalone="yes"?>
<Paper uid="P91-1006">
  <Title>A THREE-LEVEL MODEL FOR PLAN EXPLORATION</Title>
  <Section position="12" start_page="44" end_page="45" type="concl">
    <SectionTitle>
IMPLEMENTATION AND
FUTURE WORK
</SectionTitle>
    <Paragraph position="0"> The model presented here has been implemented in a system called Pragma (redone from the earlier Pragma system \[RamSOb\]) which handles the examples covered in the paper. Since the focus is on modeling plan exploration strategies, the initial context is directly input in the form of a domain plan with its parameter values, and the queries are input as meaning representations. The output after each query is the updated set of context models.</Paragraph>
    <Paragraph position="1"> The system has been exercised in the banking and course registration domains, though it is only populated with enough domain plans to serve as a testbed for the plan exploration strategies. The exploration level is the most developed, including metaplans for constraining or instantiating plan variables and for exploring or comparing subplans using various strategies. The discourse level currently includes only the metaplans ask-value, askplans, and ask-fillers.</Paragraph>
    <Paragraph position="2"> Important next steps include expanding the collection of exploration level metaplans from the samples worked out so far to better characterize the full range of plan exploration strategies that people actually use, validating that collection against real data. It would be particularly interesting to add coverage for the hypothetical queries discussed above, where the assumed event is another known domain plan. The coverage of discourse level metaplans should be expanded, to better explore their interaction with exploration plans. The system should also be made sensitive to other indicators for recognizing moves between the exploration and domain levels besides the class of predicate queried, including verb  mood, cue phrases, and direct inform statements by the agent.</Paragraph>
  </Section>
class="xml-element"></Paper>