Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical feedback with language, prior knowledge, and common sense. We introduce Prompted Policy Search (ProPS), a novel RL method that unifies numerical and linguistic reasoning within a single framework. Unlike prior work that augments existing RL components with language, ProPS places a large language model (LLM) at the center of the policy optimization loop--directly proposing policy updates based on both reward feedback and natural language input. We show that LLMs can perform numerical optimization in-context, and that incorporating semantic signals, such as goals, constraints, and strategy hints can lead to more informed exploration and sample-efficient learning. ProPS is evaluated across 15 Gymnasium tasks, spanning classic control, Atari games, and MuJoCo environments, and compared to seven widely-adopted RL algorithms (e.g., PPO, SAC, TRPO). It outperforms all baselines on 8 out of 15 tasks and demonstrates substantial gains when provided with domain knowledge.

China-based actors are likely behind the use of ChatGPT for "covert influence operations" aimed at stoking opposition to data centres in the United States, OpenAI has said. In a research report released on Wednesday, the company behind the world's most popular AI chatbot said it had banned a cluster of accounts likely based in China for attempting to "manipulate a legitimate debate about American AI". Among other content, the accounts generated a comic strip showing a cigar-chomping businessman holding bags marked with dollar signs as a family reacted in shock to their electricity bill, according to the San Francisco-based company. OpenAI said a second cluster of accounts had generated content casting US tariffs as an effort to "dominate technological competition" with China, and specified that the material should not mention Chinese leader Xi Jinping. While the campaign sought to "exploit and amplify existing public concerns" about energy prices, OpenAI found no evidence that it had a "meaningful" influence, the company said.

A group of high school students arrested over allegedly trying to extort money from a boy in western Tokyo may have used ChatGPT to decide how much to demand, police said. A group of high school students in Tokyo arrested over allegedly assaulting a boy and trying to extort money from him may have used ChatGPT to decide how much to demand, media reports have recently revealed. Five teenagers, including a 17-year-old girl and four boys ranging in age from 16 to 17, were arrested in January over the alleged assault and attempted extortion of a 17-year-old high school student in the city of Hachioji in western Tokyo, according to the Metropolitan Police Department. Police said the suspects assaulted the boy in a plaza in Hachioji's Shiroyamate district, breaking his nose and causing other injuries, before allegedly trying to extort ¥150,000 ($935) from him. The girl, who was the victim's ex-girlfriend, allegedly first confronted him, accusing him of touching her younger sister's leg. She then challenged him, saying, "Give me the money or fight me one-on-one," according to reports by Fuji TV.

Anthropic Walks Back Policy That Could Have'Sabotaged' AI Researchers Using Claude The company changed course after researchers spoke out against the policy, which would have covertly limited Claude's ability to develop competing AI models. Anthropic is backtracking on a policy that would have covertly limited competitors from using its new AI model, Claude Fable 5, to develop other AI models. The company changed course after the move received significant backlash from the AI research community . "We're changing Fable 5's safeguards for frontier LLM development to make them visible," Anthropic said in a statement to WIRED. "We made the wrong tradeoff and we apologize for not getting the balance right."

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversary-specified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored.

Consistency learning with feature perturbation is a widely used strategy in semi-supervised medical image segmentation. However, many existing perturbation methods rely on dropout, and thus require a careful manual tuning of the dropout rate, which is a sensitive hyperparameter and often difficult to optimize and may lead to suboptimal regularization. To overcome this limitation, we propose VQ-Seg, the first approach to employ vector quantization (VQ) to discretize the feature space and introduce a novel and controllable Quantized Perturbation Module (QPM) that replaces dropout.

We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the domain of agriculture, MIRAGE captures the full complexity of expert consultations by combining natural user queries, expert-authored responses, and image-based context, offering a high-fidelity benchmark for evaluating models on grounded reasoning, clarification strategies, and long-form generation in a real-world, knowledge-intensive domain. Grounded in over 35,000 real user-expert interactions, and curated through a carefully designed multi-step pipeline, MIRAGE spans diverse crop health, pest diagnosis, and crop management scenarios. The benchmark includes more than 7,000 unique biological entities, covering plant species, pests, and diseases, making it one of the most taxonomically diverse benchmarks available for vision-language models in real-world expert-guided domains. Unlike existing benchmarks that rely on well-specified user inputs, MIRAGE features underspecified, context-rich scenarios, requiring models to infer latent knowledge gaps and either proactively guide the interaction or respond. Our benchmark comprises two core components. The Single-turn Challenge to reason over a single user turn and image set, identify relevant entities, infer causal explanations, and generate actionable recommendations; and a Multi-Turn challenge for dialogue state tracking, goal-driven generation, and expert-level conversational decision-making. We evaluate more than 20 closed and open-source frontier vision-language models (VLMs), using three reasoning language models as evaluators, highlighting the significant challenges posed by MIRAGE in both single-turn and multi-turn interaction settings. Even the advanced GPT4.1 and GPT4o models achieve 44.6% and 40.9% accuracy, respectively, indicating significant room for improvement.

Dipu Tamang from Nepal is among more than 400,000 international students in Japan. When Dipu Tamang arrived in Japan from Nepal in 2024, he joined a growing stream of young people who see the country less as a traditional study destination and more as a structured route into work and long-term opportunity. The 22-year-old graduated from Shinjuku Heiwa Japanese Language School in March and now studies international business at a vocational college in Tokyo. He juggles part-time work as a convenience store clerk and hotel housekeeper to help cover his living expenses. "At first, I was interested in Japanese pop culture," he said. "Then I wanted to learn the language.

North Korea will'never' get nuclear recognition, EU and South Korea say European Commission President Ursula von der Leyen shakes hands with South Korean President Lee Jae Myung next to European Council President Antonio Costa on the day of an EU-South Korea summit in Brussels on Wednesday. South Korea and the European Union have said that North Korea will "never" be recognized as a nuclear-weapon state, reaffirming their commitment to denuclearization days after China and North Korea pledged closer ties at a summit that made no public mention of the issue. South Korean President Lee Jae Myung held talks with European Commission President Ursula von der Leyen and European Council President Antonio Costa on Wednesday in Brussels, where they agreed to step up defense ties, including efforts to facilitate the exchange of classified information. "The DPRK will never be accepted as a nuclear-weapon state," the EU and South Korea said in a joint statement, referring to North Korea's formal name, the Democratic People's Republic of Korea. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.

Several countries have been considering tightening rules around AI use as well as social media use for children. OTTAWA - The Canadian government introduced a digital safety bill on Wednesday that would ban social media for children under 16 with exemptions for platforms that meet certain safety standards, months after Australia enacted the world's first social media ban for young people. The bill also aims to make AI chatbots safer by setting up a digital regulator to establish safety standards, a government official said. Companies could face penalties of 3% of global revenue or up to 10 million Canadian dollars ($7.2 million), whichever is more, for failing to comply. "Social media platforms and AI chatbots are designed to capture attention. They do not support healthy childhood development and have become a source of anxiety, isolation, depression and a range of other mental health challenges for many young Canadians," said Marc Miller, minister of Canadian identity and culture.