Reproduce “Jeva: System One Models from First Principles” 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
Qi Li, Xinchao Wang
Jeva makes typed decisions over requests and reusable candidate sets, including choices, Boolean judgments, and numeric scores. It encodes options separately, then lets each request representation read the full set before scoring, while caching option computations. On MLDR, hybrid caching reduced median latency from 2,102.0 ms to 75.1 ms for novel sets, with no decision changes in tested cache conditions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.