Benzoic acid and its derivative benzoate are widely utilized as food preservatives. This paper presents a highly sensitive method for detecting benzoic acid using a cross-shaped aluminum resonator integrated on top of a polyimide substrate. The resonance dip for benzoic acid was designed to be at 0.93 THz. The terahertz (THz) transmission spectrum was simulated using a designed structure with varying thicknesses of benzoic acid. Analysis of the spectral response of the THz resonance dips to the thickness of the benzoic acid layer shows that the amplitude of the resonance dips generally increases with an increase in the benzoic acid concentration. The spectral frequency shifts and transmission intensities both demonstrate high sensitivity of the metasurface sensor to trace benzoic acid thicknesses. The sensor exhibits a sensitivity of approximately 0.247 THz/RIU (Refractive Index Unit) and FOM (figure of merit) of 3.927/RIU. The THz metasurface sensor is a fast and accurate sensing tool that can detect trace substances, making it crucial in the field of food safety.

Financial return prediction increasingly relies on both financial text and structured market covariates, but adapting large language models across financial institutions remains difficult because raw data cannot be centralized and clients often exhibit heterogeneous, non-stationary market signals. This paper studies data-local federated financial return prediction with a frozen LLM, aiming to share useful cross-client adaptation while preserving client-specific predictive behavior. We propose a federated routed-adapter framework in which the server maintains a pool of lightweight adapter prototypes, each client selects a personalized mixture of these prototypes through projected directional routing, and local residual adapters are learned on private client data around the selected mixture. The server then maps uploaded residual updates back to the shared prototype space through an exact least-norm decomposition for communication-efficient aggregation. The framework keeps raw financial data and client-private prediction heads local, while uploaded residuals remain model updates and should not be interpreted as a formal privacy guarantee without additional mechanisms such as secure aggregation or differential privacy. Across FNSPID, Qlib CSI300/CSI800, and Open FinLLM forecasting benchmarks, our method achieves the best overall performance, improving CSI300 RankIC from $0.082$ to $0.087$ over the strongest federated PEFT baseline and reducing FNSPID MAE from $0.00537$ to $0.00482$. These results suggest that compositional shared adaptation with local residual personalization is a practical direction for financial LLM deployment under data-local, communication-constrained, and heterogeneous federated settings.

Memory-augmented language agents are increasingly used for long-horizon personalized interaction, but they still struggle to adapt to user-specific evidence without gradually drifting away from a stable and reliable persona. In this paper, we study how to maintain long-term persona invariance while preserving the utility of memory-based personalization. We propose a verification-aware memory framework that separates fast-changing episodic memory from a slow persona state and treats persona evolution as a controlled state transition rather than an unconstrained memory write. At a high level, retrieved evidence can only induce a bounded tentative persona update, and the update is committed only if an external verifier confirms that the resulting symbolic trace satisfies explicit persona specifications. Across long-term memory, personalized dialogue, persona consistency, and over-personalization benchmarks, our method achieves the best overall performance, improving utility metrics on LongMemEval, LoCoMo, and PersonaMem-v2 while reducing hard violation rate from 6.9 to 3.2 and increasing repair success rate from 67.5 to 74.9 on reliability benchmarks. These results show that explicit verification can make memory-augmented agents both more adaptive and more dependable, offering a practical path toward safer long-term personalization.