Abstract
DeepDebater organizes policy debate into specialized agent workflows for evidence retrieval, argument construction, cross-examination, and rebuttal. It supports autonomous and human-AI rounds, with a presentation pipeline for speech and video. The paper reports preliminary evaluations of the system.
Type
Publication
AAAI 2026 CLIP Workshop
Ravid Shwartz Ziv
AI Researcher
AI researcher at Meta MSL with a background in information theory and computational neuroscience, working on world models, memory, and compression. Former Assistant Professor and Faculty Fellow at NYU. My industry experience spans Wand AI, Intel, Google AI, and Wikipedia.