Reproduce “LLM-Assisted Coalition Formation for Cooperative Perception in Autonomous Driving” 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
Ahmad Sarlak, Hao Wang, Rahul Amin, Abolfazl Razi
The method selects fixed-size vehicle helper groups for cooperative driving by balancing observation diversity with link throughput and transmission energy, then sends structured summaries to an LLM. It uses DPP-inspired log-determinant and networking scores. In equal-power synthetic tests, it achieves higher coalition utility and networking score than k-DPP, but lower diversity; this supports a balance, not broad safety gains.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.