Researcher
2 developments in the corpus
Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.
Latest
Everything in the corpus, newest first.
This is an unrefereed arXiv preprint describing a novel method for training language model agents; it reports improvements over a baseline in a controlled setting but has not undergone peer review.
An early-stage methodological contribution introducing a replay control primitive for RL-based model training, demonstrated across multiple benchmarks but without peer review, head-to-head comparisons to all baselines, or published validation.