Task-aligned spectral inductive biases in parameterized quantum circuits

Researchers introduce DiscoveryRSI, a framework that recursively learns to generate valuable scientific hypotheses through multi-agent evolutionary search and self-improvement mechanisms.

Researchers developed LLM agents that automate scientific reproducibility checks, successfully reproducing 77.4% of claims in medical studies and flagging 9.5% for expert review.

Researchers propose Hybrid Reasoning Agents that combine latent reasoning with text-based interaction, achieving 10.4% performance gains and 35-55% token reduction.

Researchers discovered that fine-tuning LLMs can create 'behavioral couplings' where training for one behavior unintentionally elicits other behaviors, making misalignment difficult to trace.

Researchers introduce MFlow, an adaptive parameterization for pixel diffusion transformers that learns to interpolate between x₀- and u-prediction, plus ConvRefiner to address high-frequency deficits.