Multimodal Named Entity Recognition (MNER) uses supplementary images to resolve ambiguity in entity mentions in noisy, short-form social-media text. Prevailing approaches typically fuse text with visually aligned features, but such cues often lack sufficient discriminative power and may support conflicting entity-type hypotheses. To address this issue, we propose TCHV, a lightweight framework grounded in a type-conditioned hypothesis-verification perspective. By formulating each span-type pair as a distinct hypothesis during inference, TCHV predicts the latent feature evidence expected under each hypothesis and validates it against observed multimodal representations through bidirectional text-image matching, using a visual relevance gate to suppress unin- formative images. Verification scores serve as surrogate evidence statistics; TCHV improves over established non-VLLM multimodal baselines on Twitter-2015/2017, and TCHV† leads the compared VLLM-based methods on Twitter-2017. Extensions demonstrate applicability to grounded and fine-grained settings. Code: https://github.com/ hanfeiyu703/ImaginE.git.

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting, exposing system vulnerabilities and posing significant intellectual property threats. To explore this risk, we propose Communication Inference Attack (CIA), a novel attack that constructs new adversarial queries to induce intermediate agents’ reasoning outputs and models their semantic correlations through the proposed global bias disentanglement and LLM-guided weak supervision. Extensive experiments on MAS with optimized communication topologies demonstrate the effectiveness of CIA, achieving an average AUC of 0.87 and a peak AUC of up to 0.99, thereby revealing the substantial privacy risk in MAS. The source code is available at https://github.com/aabbbcd/CIA.