Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However, the pervasive issue of alpha decay-where factors lose their predictive power over time-poses a significant challenge for alpha mining. Traditional methods such as genetic programming are prone to rapid alpha decay, primarily due to their susceptibility to overfitting. At the same time, approaches driven by Large Language Models (LLMs), despite their promise, often fail to impose regularization against factor homogenization-resulting in crowded signals and accelerated decay. To address this challenge, we propose AlphaAgent, an autonomous framework that effectively integrates LLM-driven agents with ad hoc regularization for mining decay-resistant alpha factors. AlphaAgent employs three key mechanisms: (i) originality enforcement through a similarity measure based on abstract syntax trees (ASTs) against existing alphas(ii) hypothesis-factor alignment via LLM-evaluated semantic consistency between market hypotheses and generated factors, and (iii) complexity control via AST-based structural constraints, preventing over-engineered constructions that are prone to overfitting. These mechanisms collectively guide the alpha generation process to balance originality, financial rationale, and adaptability to evolving market conditions, mitigating the risk of alpha decay. Extensive evaluations show that AlphaAgent outperforms traditional and LLM-based methods in mitigating alpha decay across bull and bear markets, consistently delivering significant alpha in Chinese CSI 500 and U.S. S&P 500 markets over the past four years. Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors.

Neuromorphic event-based cameras are bio-inspired visual sensors with asynchronous pixels and extremely high temporal resolution. Such favorable properties make them an excellent choice for solving state estimation tasks under high-speed maneuvers. However, failures of camera pose tracking are frequently witnessed in state-of-the-art event-based visual odometry systems when the local map cannot be updated timely or feature matching is unreliable. One of the biggest roadblocks in this field is the absence of efficient and robust methods for data association without imposing any assumptions on the environment. This problem seems, however, unlikely to be addressed as in standard vision because of the motion-dependent nature of event data. To address this, we propose a map-free design for event-based visual-inertial state estimation in this paper. Instead of estimating camera position, we find that recovering the instantaneous linear velocity aligns better with event cameras' differential working principle. The proposed system uses raw data from a stereo event camera and an inertial measurement unit (IMU) as input, and adopts a dual-end architecture. The front-end preprocesses raw events and executes the computation of normal flow and depth information. To handle the temporally non-equispaced event data and establish association with temporally non-aligned IMU's measurements, the back-end employs a continuous-time formulation and a sliding-window scheme that can progressively estimate the linear velocity and IMU's bias. Experiments on synthetic and real data show our method achieves low-latency, metric-scale velocity estimation. To the best of our knowledge, this is the first real-time, purely event-based visual-inertial state estimator for high-speed maneuvers, requiring only sufficient textures and imposing no additional constraints on either the environment or motion pattern.