Witnessed by the recent advancements on leveraging LLM for coding and multimodal understanding, we present WebGen-V, a new benchmark and framework for instruction-to-HTML generation that enhances both data quality and evaluation granularity. WebGen-V contributes three key innovations: (1) an unbounded and extensible agentic crawling framework that continuously collects real-world webpages and can leveraged to augment existing benchmarks; (2) a structured, section-wise data representation that integrates metadata, localized UI screenshots, and JSON-formatted text and image assets, explicit alignment between content, layout, and visual components for detailed multimodal supervision; and (3) a section-level multimodal evaluation protocol aligning text, layout, and visuals for high-granularity assessment. Experiments with state-of-the-art LLMs and ablation studies validate the effectiveness of our structured data and section-wise evaluation, as well as the contribution of each component. To the best of our knowledge, WebGen-V is the first work to enable high-granularity agentic crawling and evaluation for instruction-to-HTML generation, providing a unified pipeline from real-world data acquisition and webpage generation to structured multimodal assessment.

Omni-modal large language models (OLLMs) aim to unify audio, vision, and text understanding within a single framework. While existing benchmarks primarily evaluate general cross-modal question-answering ability, it remains unclear whether OLLMs achieve modality-invariant reasoning or exhibit modality-specific biases. We introduce XModBench, a large-scale tri-modal benchmark explicitly designed to measure cross-modal consistency. XModBench comprises 60,828 multiple-choice questions spanning five task families and systematically covers all six modality compositions in question-answer pairs, enabling fine-grained diagnosis of an OLLM's modality-invariant reasoning, modality disparity, and directional imbalance. Experiments show that even the strongest model, Gemini 2.5 Pro, (i) struggles with spatial and temporal reasoning, achieving less than 60% accuracy, (ii) reveals persistent modality disparities, with performance dropping substantially when the same semantic content is conveyed through audio rather than text, and (iii) shows systematic directional imbalance, exhibiting lower consistency when vision serves as context compared to text. These findings indicate that current OLLMs remain far from truly modality-invariant reasoning and position XModBench as a fundamental diagnostic tool for evaluating and improving cross-modal competence. All data and evaluation tools will be available at https://xingruiwang.github.io/projects/XModBench/.

For multilingual factual knowledge assessment of LLMs, benchmarks such as MLAMA use template translations that do not take into account the grammatical and semantic information of the named entities inserted in the sentence. This leads to numerous instances of ungrammaticality or wrong wording of the final prompts, which complicates the interpretation of scores, especially for languages that have a rich morphological inventory. In this work, we sample 4 Slavic languages from the MLAMA dataset and compare the knowledge retrieval scores between the initial (templated) MLAMA dataset and its sentence-level translations made by Google Translate and ChatGPT. We observe a significant increase in knowledge retrieval scores, and provide a qualitative analysis for possible reasons behind it. We also make an additional analysis of 5 more languages from different families and see similar patterns. Therefore, we encourage the community to control the grammaticality of highly multilingual datasets for higher and more interpretable results, which is well approximated by whole sentence translation with neural MT or LLM systems. The dataset and all related code is published at the Github repository: https://github.com/ZurichNLP/Fluent-mLAMA.

When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at https://intentassistant.github.io

Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requires both reasoning and effective tool use. A central challenge for agentic tasks is the growing context length, as agents must accumulate long histories of actions and observations. This expansion raises costs and reduces efficiency in long-horizon tasks, yet prior work on context compression has mostly focused on single-step tasks or narrow applications. We introduce Agent Context Optimization (ACON), a unified framework that optimally compresses both environment observations and interaction histories into concise yet informative condensations. ACON leverages compression guideline optimization in natural language space: given paired trajectories where full context succeeds but compressed context fails, capable LLMs analyze the causes of failure, and the compression guideline is updated accordingly. Furthermore, we propose distilling the optimized LLM compressor into smaller models to reduce the overhead of the additional module. Experiments on AppWorld, OfficeBench, and Multi-objective QA show that ACON reduces memory usage by 26-54% (peak tokens) while largely preserving task performance, preserves over 95% of accuracy when distilled into smaller compressors, and enhances smaller LMs as long-horizon agents with up to 46% performance improvement. Our code is available at https://github.com/microsoft/acon.

Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of these techniques is the Independence of Irrelevant Alternatives (IIA) assumption, which collapses \emph{all} human preferences to a universal underlying utility function, yielding a coarse approximation of the range of human preferences. On the other hand, statistical and computational guarantees for models avoiding this assumption are scarce. In this paper, we investigate the statistical and computational challenges of learning a \emph{correlated} probit model, a fundamental RUM that avoids the IIA assumption. First, we establish that the classical data collection paradigm of pairwise preference data is \emph{fundamentally insufficient} to learn correlational information, explaining the lack of statistical and computational guarantees in this setting. Next, we demonstrate that \emph{best-of-three} preference data provably overcomes these shortcomings, and devise a statistically and computationally efficient estimator with near-optimal performance. These results highlight the benefits of higher-order preference data in learning correlated utilities, allowing for more fine-grained modeling of human preferences. Finally, we validate these theoretical guarantees on several real-world datasets, demonstrating improved personalization of human preferences.

A new survey from the Center for Democracy and Technology reveals nearly 20% of U.S. high school students use AI for romantic relationships.

Our great big world captured in beautiful detail. Breakthroughs, discoveries, and DIY tips sent every weekday. In 1839, photography as a medium was made widely available to the public. Named in honor of photography's milestone year, the 1839 Awards celebrates stunning imagery from around the world. This year's competition welcomed entries from 79 countries and awarded winners across professional and non-professional categories.

W hen the first ever stage adaptation of the global book and film franchise The Hunger Games opens its doors in London next week, fans paying up to £200 have been promised an "electrifying" and "immersive" experience. The show at the purpose-built 1,200 seat Troubadour in Canary Wharf, which features Hollywood A-lister John Malkovich appearing via screen as the evil President Snow who oversees the televised spectacle of teenagers fighting to the death, is the latest in an explosion of launches looking to cash in on a boom in consumer demand for experiential entertainment, often linked to bankable franchises. The boom in the market for experimental, unusual nights out and shows is well established, from escape rooms, axe throwing and slumber parties to Secret Cinema's Olympic Park takeover to recreate the setting for Back to the Future and the hugely successful Abba Voyage. Recent pop-ups include experiences linked to Minecraft, Jurassic World and Squid Game. As big money has rolled into the sector, so too has a desire from companies to rely on solid gold intellectual property to bring in the crowds - with mixed results.

Sign up to receive it in your inbox. In " Final Boy," your story in this week's issue, Rick is a writer of fan fiction about the eighties sitcom "Charles in Charge." How does Rick think of his writing, and how does it fit into his conception of himself? Rick is a guy who has always loved books and used to study creative writing. He's worked for decades in the gig economy, long before it was even called that, doing freelance copy editing and the like.