DeepInflation: an AI agent for research and model discovery of inflation

We present \textbf{DeepInflation}, an AI agent designed for research and model discovery in inflationary cosmology. Built upon a multi-agent architecture, \textbf{DeepInflation} integrates Large Language Models (LLMs) with a symbolic regression (SR) engine and a retrieval-augmented generation (RAG) knowledge base. This framework enables the agent to automatically explore and verify the vast landscape of inflationary potentials while grounding its outputs in established theoretical literature. We demonstrate that \textbf{DeepInflation} can successfully discover simple and viable single-field slow-roll inflationary potentials consistent with the latest observations (here ACT DR6 results as example) or any given $n_s$ and $r$, and provide accurate theoretical context for obscure inflationary scenarios. \textbf{DeepInflation} serves as a prototype for a new generation of autonomous scientific discovery engines in cosmology, which enables researchers and non-experts alike to explore the inflationary landscape using natural language. This agent is available at https://github.com/pengzy-cosmo/DeepInflation.

News-Aware Direct Reinforcement Trading for Financial Markets

The financial market is known to be highly sensitive to news. Therefore, effectively incorporating news data into quantitative trading remains an important challenge. Existing approaches typically rely on manually designed rules and/or handcrafted features. In this work, we directly use the news sentiment scores derived from large language models, together with raw price and volume data, as observable inputs for reinforcement learning. These inputs are processed by sequence models such as recurrent neural networks or Transformers to make end-to-end trading decisions. We conduct experiments using the cryptocurrency market as an example and evaluate two representative reinforcement learning algorithms, namely Double Deep Q-Network (DDQN) and Group Relative Policy Optimization (GRPO). The results demonstrate that our news-aware approach, which does not depend on handcrafted features or manually designed rules, can achieve performance superior to market benchmarks. We further highlight the critical role of time-series information in this process.