Generative agents are rapidly advancing in sophistication, raising urgent questions about how they might coordinate when deployed in online ecosystems. This is particularly consequential in information operations (IOs), influence campaigns that aim to manipulate public opinion on social media. While traditional IOs have been orchestrated by human operators and relied on manually crafted tactics, agentic AI promises to make campaigns more automated, adaptive, and difficult to detect. This work presents the first systematic study of emergent coordination among generative agents in simulated IO campaigns. Using generative agent-based modeling, we instantiate IO and organic agents in a simulated environment and evaluate coordination across operational regimes, from simple goal alignment to team knowledge and collective decision-making. As operational regimes become more structured, IO networks become denser and more clustered, interactions more reciprocal and positive, narratives more homogeneous, amplification more synchronized, and hashtag adoption faster and more sustained. Remarkably, simply revealing to agents which other agents share their goals can produce coordination levels nearly equivalent to those achieved through explicit deliberation and collective voting. Overall, we show that generative agents, even without human guidance, can reproduce coordination strategies characteristic of real-world IOs, underscoring the societal risks posed by increasingly automated, self-organizing IOs.

We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a prevalent source of information online, it is essential for RAG systems to integrate information from these sources into generation. However, existing evaluations for RAG are text-centric, limiting their applicability to multimodal, reasoning intensive settings because they don't verify information against sources. MiRAGE is a claim-centric approach to multimodal RAG evaluation, consisting of InfoF1, evaluating factuality and information coverage, and CiteF1, measuring citation support and completeness. We show that MiRAGE, when applied by humans, strongly aligns with extrinsic quality judgments. We additionally introduce automatic variants of MiRAGE and three prominent TextRAG metrics -- ACLE, ARGUE, and RAGAS -- demonstrating the limitations of text-centric work and laying the groundwork for automatic evaluation. We release open-source implementations and outline how to assess multimodal RAG.

Room impulse response (RIR) generation remains a critical challenge for creating immersive virtual acoustic environments. Current methods suffer from two fundamental limitations: the scarcity of full-band RIR datasets and the inability of existing models to generate acoustically accurate responses from diverse input modalities. We present PromptReverb, a two-stage generative framework that addresses these challenges. Our approach combines a variational autoencoder that upsamples band-limited RIRs to full-band quality (48 kHz), and a conditional diffusion transformer model based on rectified flow matching that generates RIRs from descriptions in natural language. Empirical evaluation demonstrates that PromptReverb produces RIRs with superior perceptual quality and acoustic accuracy compared to existing methods, achieving 8.8% mean RT60 error compared to -37% for widely used baselines and yielding more realistic room-acoustic parameters. Our method enables practical applications in virtual reality, architectural acoustics, and audio production where flexible, high-quality RIR synthesis is essential.

The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework (DPRF). DPRF aims to optimize the alignment of LLM RPAs' behaviors with those of target individuals by iteratively identifying the cognitive divergence, either through free-form or theory-grounded, structured analysis, between generated behaviors and human ground truth, and refining the persona profile to mitigate these divergences. We evaluate DPRF with five LLMs on four diverse behavior-prediction scenarios: formal debates, social media posts with mental health issues, public interviews, and movie reviews. DPRF can consistently improve behavioral alignment considerably over baseline personas and generalizes across models and scenarios. Our work provides a robust methodology for creating high-fidelity persona profiles and enhancing the validity of downstream applications, such as user simulation, social studies, and personalized AI.

While Large Language Models (LLMs) have made agentic AI, chatbots, and other intelligent applications possible, they have also enabled the affordable creation of highly convincing AI-generated disinformation (Bontcheva et al., 2024), which poses a systemic risk to democratic stability and global security (VIGINUM, 2025; Bengio, 2025). Initially, AI-generated texts suffered from linguistic mistakes and thus were more easily detectable by humans. However, modern LLMs, particularly instruction-tuned models, have significantly improved in producing outputs which are indistinguishable from human-written text (Spitale et al., 2023; Heppell et al., 2024). These advances have resulted in their misuse in generating persuasive disinformation narratives, including political manipulation, health disinformation, conspiracy propagation, and Foreign Information Manipulation and Interference (FIMI) (Vykopal et al., 2024; Chen and Shu, 2024a; Barman et al., 2024; Chen and Shu, 2024b; Heppell et al., 2024; VIGINUM, 2025). While there is a growing body of research on the generation and detection of LLM-produced disinformation (Chen and Shu, 2024a; Lucas et al., 2023; Vykopal et al., 2024; Heppell et al., 2024), a critical aspect remains largely unstudied - namely, whether LLMs are capable of generating fluent and convincing personalised disinformation (i.e., disinformation narratives tailored to specific audiences) in multiple languages and at scale. The few prior studies on AIgenerated personalised disinformation are limited to English and address a very narrow set of personas (e.g., students, parents) (Zugecova et al., 2024). Crucially, prior work has not yet examined whether LLMs can adapt disinformation to country-specific linguistic and cultural contexts in multiple languages.

Based on 230 visualisations, this paper examines the depiction of museum curators by the popular generative Artificial Intelligence (AI) model, ChatGPT4o. While the AI-generated representations do not reiterate popular stereotypes of curators as nerdy, conservative in dress and stuck in time rummaging through collections, they contrast sharply with real-world demographics. AI-generated imagery extremely underrepresents women (3.5% vs 49% to 72% in reality) and disregards ethnic communities other than Caucasian (0% vs 18% to 36%). It only over-represents young curators (79% vs approx. 27%) but also renders curators to resemble yuppie professionals or people featuring in fashion advertising. Stereotypical attributes are prevalent, with curators widely depicted as wearing beards and holding clipboards or digital tablets. The findings highlight biases in the generative AI image creation dataset, which is poised to shape an inaccurate portrayal of museum professionals if the images were to be taken uncritically at face value.

Generative AI systems for music and video commonly use text-based filters to prevent the regurgitation of copyrighted material. We expose a fundamental flaw in this approach by introducing Adversarial PhoneTic Prompting (APT), a novel attack that bypasses these safeguards by exploiting phonetic memorization. The APT attack replaces iconic lyrics with homophonic but semantically unrelated alternatives (e.g., "mom's spaghetti" becomes "Bob's confetti"), preserving acoustic structure while altering meaning; we identify high-fidelity phonetic matches using CMU pronouncing dictionary. We demonstrate that leading Lyrics-to-Song (L2S) models like SUNO and YuE regenerate songs with striking melodic and rhythmic similarity to their copyrighted originals when prompted with these altered lyrics. More surprisingly, this vulnerability extends across modalities. When prompted with phonetically modified lyrics from a song, a Text-to-Video (T2V) model like Veo 3 reconstructs visual scenes from the original music video-including specific settings and character archetypes-despite the absence of any visual cues in the prompt. Our findings reveal that models memorize deep, structural patterns tied to acoustics, not just verbatim text. This phonetic-to-visual leakage represents a critical vulnerability in transcript-conditioned generative models, rendering simple copyright filters ineffective and raising urgent concerns about the secure deployment of multimodal AI systems. Demo examples are available at our project page (https://jrohsc.github.io/music_attack/).

Trustworthy language models should provide both correct and verifiable answers. However, citations generated directly by standalone LLMs are often unreliable. As a result, current systems insert citations by querying an external retriever at inference time, introducing latency, infrastructure dependence, and vulnerability to retrieval noise. We explore whether LLMs can be made to reliably attribute to the documents seen during continual pretraining without test-time retrieval, by revising the training process. To study this, we construct CitePretrainBench, a benchmark that mixes real-world corpora (Wikipedia, Common Crawl, arXiv) with novel documents and probes both short-form (single-fact) and long-form (multi-fact) citation tasks. Our approach follows a two-stage process: (1) continual pretraining to index factual knowledge by binding it to persistent document identifiers; and (2) instruction tuning to elicit citation behavior. We introduce Active Indexing for the first stage, which creates generalizable, source-anchored bindings by augmenting training with synthetic data that (i) restate each fact in diverse, compositional forms and (ii) enforce bidirectional training (source-to-fact and fact-to-source). This equips the model to both generate content from a cited source and attribute its own answers, improving robustness to paraphrase and composition. Experiments with Qwen-2.5-7B&3B show that Active Indexing consistently outperforms a Passive Indexing baseline, which simply appends an identifier to each document, achieving citation precision gains of up to 30.2% across all tasks and models. Our ablation studies reveal that performance continues to improve as we scale the amount of augmented data, showing a clear upward trend even at 16x the original token count. Finally, we show that internal citations complement external ones by making the model more robust to retrieval noise.

Environment Animals Wildlife Spiders Spiders'decorate' their webs to help trap dinner Stabilimenta may help spiders find a buggy snack. Breakthroughs, discoveries, and DIY tips sent every weekday. One of nature's most beautiful natural wonders, spider webs sometimes feature little extra bits of flair called stabilimenta . Stabilimenta are highly-reflective UV structures. Basically, think of them like spidey bike reflectors scattered throughout a web.

Biologists investigate the case of the lost'bone devourers' that feed on whale carcasses. Osedax is considered an ecosystem engineer. Breakthroughs, discoveries, and DIY tips sent every weekday. If you're leading a group of zombie apocalypse survivors, you don't want to lose sight of the horde of brain-hungry creatures trying to eat you. The same can be said if the zombie worm goes missing from the ocean floor.