This paper addresses the problem of both actively searching and tracking multiple unknown dynamic objects in a known environment with multiple cooperative autonomous agents with partial observability. The tracking of a target ends when the uncertainty is below a threshold. Current methods typically assume homogeneous agents without access to external information and utilize short-horizon target predictive models. Such assumptions limit real-world applications. We propose a fully integrated pipeline where the main contributions are: (1) a time-varying weighted belief representation capable of handling knowledge that changes over time, which includes external reports of varying levels of trustworthiness in addition to the agents; (2) the integration of a Long Short Term Memory-based trajectory prediction within the optimization framework for long-horizon decision-making, which reasons in time-configuration space, thus increasing responsiveness; and (3) a comprehensive system that accounts for multiple agents and enables information-driven optimization. When communication is available, our strategy consolidates exploration results collected asynchronously by agents and external sources into a headquarters, who can allocate each agent to maximize the overall team's utility, using all available information. We tested our approach extensively in simulations against baselines, and in robustness and ablation studies. In addition, we performed experiments in a 3D physics based engine robot simulator to test the applicability in the real world, as well as with real-world trajectories obtained from an oceanography computational fluid dynamics simulator. Results show the effectiveness of our method, which achieves mission completion times 1.3 to 3.2 times faster in finding all targets, even under the most challenging scenarios where the number of targets is 5 times greater than that of the agents.

Parameter-efficient tuning (PEFT) techniques like low-rank adaptation (LoRA) offer training efficiency on Large Language Models, but their impact on model performance remains limited. Recent efforts integrate LoRA and Mixture-of-Experts (MoE) to improve the performance of PEFT methods. Despite promising results, research on improving the efficiency of LoRA with MoE is still in its early stages. Recent studies have shown that experts in the MoE architecture have different strengths and also exhibit some redundancy. Does this statement also apply to parameter-efficient MoE? In this paper, we introduce a novel parameter-efficient MoE method, \textit{\textbf{M}oE-L\textbf{o}RA with \textbf{L}ayer-wise Expert \textbf{A}llocation (MoLA)} for Transformer-based models, where each model layer has the flexibility to employ a varying number of LoRA experts. We investigate several architectures with varying layer-wise expert configurations. Experiments on six well-known NLP and commonsense QA benchmarks demonstrate that MoLA achieves equal or superior performance compared to all baselines. We find that allocating more LoRA experts to higher layers further enhances the effectiveness of models with a certain number of experts in total. With much fewer parameters, this allocation strategy outperforms the setting with the same number of experts in every layer. This work can be widely used as a plug-and-play parameter-efficient tuning approach for various applications. The code is available at https://github.com/GCYZSL/MoLA.