Reproduce “Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Casey Kennington, Pierre Lison, David Schlangen
The authors review incremental dialogue management for robots, finding decision-making less studied than incremental speech recognition and language generation. They discuss systems that decide as speech unfolds and revise decisions when later input changes an interpretation. In a prior puzzle-game study, incremental interaction received higher human-likeness and reactivity ratings, but not helpfulness. The review proposes research requirements rather than evaluating a robot system.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.