Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we take a trip around some of the RoboCup leagues, check in at ICML, learn about the NASA onboard AI research platform, and explore feedback in human-robot interactions. This month saw the running of RoboCup 2025, with the event taking place in Salvador, Brazil, from 15-21 July. Ahead of kick-off, we spoke to the general chair Marco Simões and caught up with Ana Patrícia Magalhães, lead organizer for RoboCupJunior, to find out more about their plans for the week. You can find out what the participants got up to in our two round-ups from social media: #RoboCup2025: social media round-up 1 #RoboCup2025: social media round-up part 2. If you missed the action, you can find the recordings of the livestreams here.

Wearable AI systems aim to provide timely assistance in daily life, but existing approaches often rely on user initiation or predefined task knowledge, neglecting users' current mental states. We introduce ProMemAssist, a smart glasses system that models a user's working memory (WM) in real-time using multi-modal sensor signals. Grounded in cognitive theories of WM, our system represents perceived information as memory items and episodes with encoding mechanisms, such as displacement and interference. This WM model informs a timing predictor that balances the value of assistance with the cost of interruption. In a user study with 12 participants completing cognitively demanding tasks, ProMemAssist delivered more selective assistance and received higher engagement compared to an LLM baseline system. Qualitative feedback highlights the benefits of WM modeling for nuanced, context-sensitive support, offering design implications for more attentive and user-aware proactive agents.

Arabic Rhetoric is the field of Arabic linguistics which governs the art and science of conveying a message with greater beauty, impact and persuasiveness. The field is as ancient as the Arabic language itself and is found extensively in classical and contemporary Arabic poetry, free verse and prose. In practical terms, it is the intelligent use of word order, figurative speech and linguistic embellishments to enhance message delivery. Despite the volumes that have been written about it and the high status accorded to it, there is no way to objectively know whether a speaker or writer has used Arabic rhetoric in a given text, to what extent, and why. There is no objective way to compare the use of Arabic rhetoric across genres, authors or epochs. It is impossible to know which of pre-Islamic poetry, Andalucian Arabic poetry, or modern literary genres are richer in Arabic rhetoric. The aim of the current study was to devise a way to measure the density of the literary devices which constitute Arabic rhetoric in a given text, as a proxy marker for Arabic rhetoric itself. A comprehensive list of 84 of the commonest literary devices and their definitions was compiled. A system of identifying literary devices in texts was constructed. A method of calculating the density of literary devices based on the morpheme count of the text was utilised. Four electronic tools and an analogue tool were created to support the calculation of an Arabic text's rhetorical literary device density, including a website and online calculator. Additionally, a technique of reporting the distribution of literary devices used across the three sub-domains of Arabic rhetoric was created. The output of this project is a working tool which can accurately report the density of Arabic rhetoric in any Arabic text or speech.

Biased data representation in AI marginalizes up to 75 million autistic people worldwide through medical applications viewing autism as a deficit of neurotypical social skills rather than an aspect of human diversity, and this perspective is grounded in research questioning the humanity of autistic people. Turing defined artificial intelligence as the ability to mimic human communication, and as AI development increasingly focuses on human-like agents, this benchmark remains popular. In contrast, we define Neuro-Inclusive AI as datasets and systems that move away from mimicking humanness as a benchmark for machine intelligence. Then, we explore the origins, prevalence, and impact of anti-autistic biases in current research. Our work finds that 90% of human-like AI agents exclude autistic perspectives, and AI creators continue to believe ethical considerations are beyond the scope of their work. To improve the autistic representation in data, we conduct empirical experiments with annotators and LLMs, finding that binary labeling schemes sufficiently capture the nuances of labeling anti-autistic hate speech. Our benchmark, AUTALIC, can be used to evaluate or fine-tune models, and was developed to serve as a foundation for more neuro-inclusive future work.

Earlier this year, we spoke to Yuki Mitsufuji, Lead Research Scientist at Sony AI, about work concerning different aspects of image generation. Yuki and his team have since extended their work to sound generation, presenting work at ICLR 2025 entitled: SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation. We caught up with Yuki to find out more. Creating sounds for different types of multimedia, such as video games and movies, takes a lot of experimenting, as artists try to match sounds to their evolving creative ideas. New high-quality diffusion-based Text-to-Sound (T2S) generative models can help with this process, but they are often slow, which makes it harder for creators to experiment quickly.

Meta told employees that it is going to allow some coding job candidates to use an AI assistant during the interview process, according to internal Meta communications seen by 404 Media. The company has also asked existing employees to volunteer for a "mock AI-enabled interview," the messages say. It's the latest indication that Silicon Valley giants are pushing software engineers to use AI in their jobs, and it signals a broader move toward hiring employees who can vibecode as part of their jobs. "AI-Enabled Interviews--Call for Mock Candidates," a post from earlier this month on an internal Meta message board reads. "Meta is developing a new type of coding interview in which candidates have access to an AI assistant. This is more representative of the developer environment that our future employees will work in, and also makes LLM-based cheating less effective."

The Stable Roommates problems are characterized by the preferences of agents over other agents as roommates. A solution is a partition of the agents into pairs that are acceptable to each other (i.e., they are in the preference lists of each other), and the matching is stable (i.e., there do not exist any two agents who prefer each other to their roommates, and thus block the matching). Motivated by real-world applications, and considering that stable roommates problems do not always have solutions, we continue our studies to compute "good-enough" matchings. In addition to the agents' habits and habitual preferences, we consider their networks of preferred friends, and introduce a method to generate personalized solutions to stable roommates problems. We illustrate the usefulness of our method with examples and empirical evaluations.

A groundbreaking program has now made it possible to preserve your life stories and wisdom, allowing you to speak to loved ones decades into the future. StoryFile, an innovative AI company, has developed lifelike, interactive 3D avatars that allow people to'live on' after death, sharing memories and answering questions in the same natural and conversational manner of a real person. Individuals like philanthropist Michael Staenberg, 71, and Star Trek star William Shatner, 94, have used StoryFile to immortalize both their experiences and personalities. Staenberg, a property developer and philanthropist who has given away more than 850 million, said: 'I hope to pass my knowledge on, and the good I've created.' The technology captures video interviews, transforming them into hologram-style avatars that use generative AI, similar to ChatGPT, to respond dynamically to questions.

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language can often provide a much richer learning medium for LLMs, compared with policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples system-level trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across four tasks, GEPA outperforms GRPO by 10% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% across two LLMs, and demonstrates promising results as an inference-time search strategy for code optimization.

Making new friends is hard. Finding out what trousers exist in the world other than black ones is also, apparently, hard. Fortunately, for an AI-enabled generation of students, help with the complexities of campus life is just a prompt away. If you are really stuck on an essay or can't decide between management consulting or a legal career, or need suggestions on what you can cook with tomatoes, mushrooms, beetroot, mozzarella, olive oil and rice, then ChatGPT is there. It will to listen to you, analyse your inputs, and offer up a perfectly structured paper, a convincing cover letter, or a workable recipe for tomato and mushroom risotto with roasted beetroot and mozzarella. I know this because three undergraduates have given me permission to eavesdrop on every conversation they have had with ChatGPT over the past 18 months.