A humanoid robot from GMO Internet Group dances and hops at the 2025 International Robot Exhibition on Wednesday in Tokyo. Robots equipped with cutting-edge technologies that perform duties on behalf of humans at workplaces and disaster-hit sites are on display at the 2025 International Robot Exhibition in Tokyo. At the exhibition, which kicked off at Tokyo Big Sight on Wednesday, the spotlight is on humanoid robots as well as those powered by artificial intelligence. Kawasaki Heavy Industries is showcasing the newest model of its humanoid robot Kaleido, which is equipped with technologies such as autonomous movement and remote control. In a demonstration held the same day, the robot extinguished a mock fire, removed a fallen shelf weighing 30 kilograms and rescued a dummy cat.

The Metropolitan Police Department arrested a 17-year-old boy on Thursday for allegedly carrying out a cyberattack on the operator of the Kaikatsu Club internet cafe chain, sources said. Tokyo police served an arrest warrant on a 17-year-old boy on Thursday for allegedly carrying out a cyberattack on the operator of the Kaikatsu Club internet cafe chain, investigative sources said. The Metropolitan Police Department arrested the second-year high school student from the city of Osaka over an alleged violation of the law against unauthorized computer access and fraudulent obstruction of business. According to the sources, the boy fraudulently obtained about 7.25 million sets of Kaikatsu Club membership information with a computer program he created using the ChatGPT artificial intelligence chatbot. The boy is said to have skills strong enough to have won awards in cybersecurity competitions, as reported by TBS.

Things to Do in L.A. Tap to enable a layout that focuses on the article. The Audrey Irmas Pavilion, left, at the Wilshire Boulevard Temple, center in background, in 2021. This is read by an automated voice. Please report any issues or inconsistencies here . Two were arrested during a pro-Palestinian protest at Wilshire Boulevard Temple that ended in confrontation.

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of model-generated answers and their preferences are used to train a reward model. However, human feedback is inherently heterogeneous, creating significant challenges for reliable reward learning. To address this, we adopt a heterogeneous preference framework that jointly models the latent reward of answers and human rationality. This leads to a challenging biconvex optimization problem, which we solve via an alternating gradient descent algorithm. We establish theoretical guarantees for the resulting estimator, including its convergence and asymptotic distribution. These results enable the construction of confidence intervals for reward estimates. Leveraging these uncertainty quantification results, we conduct valid statistical comparisons between rewards and incorporate uncertainty into the best-of-$N$ (BoN) policy framework. Extensive simulations demonstrate the effectiveness of our method, and applications to real LLM data highlight the practical value of accounting for uncertainty in reward modeling for LLM alignment.

Reasoning models leveraging long chains of thought employ various cognitive skills, such as verification of their answers, backtracking, retrying by an alternate method, and more. Previous work has shown that when a base language model exhibits these skills, training that model further with reinforcement learning (RL) can learn to leverage them. How can we get models to leverage skills that aren't exhibited by base models? Our work, SkillFactory, is a method for fine-tuning models to roughly learn these skills during a supervised fine-tuning (SFT) stage prior to RL. Our approach does not rely on distillation from a stronger model, but instead uses samples from the model itself, rearranged to provide training data in the format of those skills. These "silver" SFT traces may be imperfect, but are nevertheless effective for priming a model to acquire skills during RL. Our evaluation shows that (1) starting from SkillFactory SFT initialization helps a model to generalize to harder variants of a task post-RL, despite lower performance pre-RL; (2) cognitive skills are indeed used by the model; (3) RLed SkillFactory models are more robust to regression on out-of-domain tasks than RLed base models. Our work suggests that inductive biases learned prior to RL help models learn robust cognitive skill use.

Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The agentic paradigm promises that VLMs can use a wide variety of tools that could augment these capabilities, such as depth estimators, segmentation models, and pose estimators. Yet it remains an open challenge how to realize this vision without solely relying on handcrafted prompting strategies or enforcing fixed, predefined tool pipelines that limit VLMs' ability to discover optimal tool-use patterns. Reinforcement Learning could overcome this gap, but has so far been limited to reasoning with a single visual tool due to the large search space in multi-tool reasoning. We introduce Double Interactive Reinforcement Learning (DIRL), a two-phase training framework where VLMs learn to coordinate multiple tools through interactive exploration and feedback. In the teaching phase, we combine demonstrations from a single tool specialist trained via interactive RL with traces from a frontier model using all tools. In the exploration phase, the model further refines multi-tool coordination through continued RL. Our model, SpaceTools, with tool-augmented spatial reasoning ability, achieves state-of-the-art performance on spatial understanding benchmarks (RoboSpatial-Home, BLINK, BOP-ASK) and demonstrates reliable real-world manipulation using a 7-DOF robot as a tool. DIRL provides substantial improvements over the vanilla SFT (+12% on RoboSpatial) and RL (+16% on RoboSpatial) baselines. Project page: https://spacetools.github.io/.

Socially interactive agents (SIAs) are being used in various scenarios and are nearing productive deployment. Evaluating user satisfaction with SIAs' performance is a key factor in designing the interaction between the user and SIA. Currently, subjective user satisfaction is primarily assessed manually through questionnaires or indirectly via system metrics. This study examines the automatic classification of user satisfaction through analysis of social signals, aiming to enhance both manual and autonomous evaluation methods for SIAs. During a field trial at the Deutsches Museum Bonn, a Furhat Robotics head was employed as a service and information hub, collecting an "in-the-wild" dataset. This dataset comprises 46 single-user interactions, including questionnaire responses and video data. Our method focuses on automatically classifying user satisfaction based on time series classification. We use time series of social signal metrics derived from the body pose, time series of facial expressions, and physical distance. This study compares three feature engineering approaches on different machine learning models. The results confirm the method's effectiveness in reliably identifying interactions with low user satisfaction without the need for manually annotated datasets. This approach offers significant potential for enhancing SIA performance and user experience through automated feedback mechanisms.

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the prompt. While literature on prompt engineering is expanding, few studies focus on classification tasks, and even fewer address domains like psychology, where constructs have precise, theory-driven definitions that may not be well represented in pre-training data. We present an empirical framework for optimizing LLM performance for identifying constructs in texts via prompt engineering. We experimentally evaluate five prompting strategies --codebook-guided empirical prompt selection, automatic prompt engineering, persona prompting, chain-of-thought reasoning, and explanatory prompting - with zero-shot and few-shot classification. We find that persona, chain-of-thought, and explanations do not fully address performance loss accompanying a badly worded prompt. Instead, the most influential features of a prompt are the construct definition, task framing, and, to a lesser extent, the examples provided. Across three constructs and two models, the classifications most aligned with expert judgments resulted from a few-shot prompt combining codebook-guided empirical prompt selection with automatic prompt engineering. Based on our findings, we recommend that researchers generate and evaluate as many prompt variants as feasible, whether human-crafted, automatically generated, or ideally both, and select prompts and examples based on empirical performance in a training dataset, validating the final approach in a holdout set. This procedure offers a practical, systematic, and theory-driven method for optimizing LLM prompts in settings where alignment with expert judgment is critical.

Multi-Agent Systems (MAS) with large language models (LLMs) enable personalized education but risk leaking minors personally identifiable information (PII) via unstructured dialogue. Existing privacy methods struggle to balance security and utility: role-based access control fails on unstructured text, while naive masking destroys pedagogical context. We propose SRPG, a privacy guard for educational MAS, using a Dual-Stream Reconstruction Mechanism: a strict sanitization stream ensures zero PII leakage, and a context reconstruction stream (LLM driven) recovers mathematical logic. This decouples instructional content from private data, preserving teaching efficacy. Tests on MathDial show SRPG works across models; with GPT-4o, it achieves 0.0000 Attack Success Rate (ASR) (zero leakage) and 0.8267 Exact Match, far outperforming the zero trust Pure LLM baseline (0.2138). SRPG effectively protects minors privacy without sacrificing mathematical instructional quality.

We present AITutor-EvalKit, an application that uses language technology to evaluate the pedagogical quality of AI tutors, provides software for demonstration and evaluation, as well as model inspection and data visualization. This tool is aimed at education stakeholders as well as *ACL community at large, as it supports learning and can also be used to collect user feedback and annotations.