Reproduce “Guided Sensemaking: Agents in Collaborative Deliberation” 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
Aaditya Bhatia, Navdeep Kaur Bhatia, Marc-Antoine Parent, Jack Park
A multiagent AI platform, Guided Sensemaking, supports collaborative deliberation by scaffolding critical thinking through dynamic visualization of individual and collective arguments. The system helps participants refine their reasoning, externalizes discourse structure, and provides facilitators with insights into evolving understanding, aiming for coherent, traceable collective sensemaking.
Key insights
- AI can be designed as a 'complementary cognitive artifact' to augment human intelligence and critical thinking, rather than displacing it.
- Explicitly externalizing reasoning through dynamic discourse graphs enhances individual reflection, metacognitive awareness, and the ability to identify inconsistencies.
- A multiagent system can effectively scaffold complex cognitive processes like argument construction and collaborative sensemaking without sacrificing user agency.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.