Metaphors are a crucial way for humans to express complex or subtle ideas by comparing one concept to another, often from a different domain.However, many large language models (LLMs) struggle to interpret and apply metaphors in multi-agent language games, hindering their ability to engage in covert communication and semantic evasion, which are crucial for strategic communication.To address this challenge, we introduce CoMet, a framework that enables LLM-based agents to engage in metaphor processing.CoMet combines a hypothesis-based metaphor reasoner with a metaphor generator that improves through self-reflection and knowledge integration.This enhances the agents' ability to interpret and apply metaphors, improving the strategic and nuanced quality of their interactions.We evaluate CoMet on two multi-agent language games-Undercover and Adversarial Taboo-which emphasize "covert communication" and "semantic evasion".Experimental results demonstrate that CoMet significantly enhances the agents' ability to communicate strategically using metaphors.

We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our approach combines the off-the-shelf active tracking methods with VLMs’ reasoning capabilities, deploying a fast visual policy for normal tracking and activating VLM reasoning only upon failure detection. The framework features a memory-augmented self-reflection mechanism that enables the VLM to progressively improve by learning from past experiences, effectively addressing VLMs’ limitations in 3D spatial reasoning. Experimental results demonstrate significant performance improvements, with our framework boosting success rates by 72% with state-of-the-art RL-based approaches and 220% with PID-based methods in challenging environments. This work represents the first integration of VLM-based reasoning to assist EVT agents in proactive failure recovery, offering substantial advances for real-world robotic applications that require continuous target monitoring in dynamic, unstructured environments. Project website: https://sites.google.com/view/evt-recovery-assistant.

With the rapid development of Internet of Things (IoT), a large amount of data is transmitted within systems, which sparks numerous applications through data processing and analysis. As an expected infrastructure of IoT, although edge computing improves the redundancy and cost of the system, security and privacy are still important research issues. In recent years, privacy-preserving data aggregation has attracted extensive research attention. Most existing schemes are based on asymmetric encryption and allow the transmission of encrypted individual data, which leads to high computation and communication costs and uncertainty for privacy. To address this, a flexible-group-based privacy-preserving aggregation scheme for multidimensional data in edge-enhanced IoT (FGAMD) is proposed in this article, which is based on symmetric encryption and Chinese remainder theorem (CRT). The homomorphic properties of the CRT are utilized to construct data aggregation groups for users, which reduces the communication burden of the gateway. Furthermore, by setting different thresholds of the aggregation groups, variable security and robustness requirements can be meet for flexible applications. Through analysis, FGAMD greatly reduces the computation cost, and due to the flexible terminal group size, the communication cost is significantly lower than that of similar strategies when the terminal group size is small.