This paper deals with improving querying large language models (LLMs). It is well-known that without relevant contextual information, LLMs can provide poor quality responses or tend to hallucinate. Several initiatives have proposed integrating LLMs with external tools to provide them with up-to-date data to improve accuracy. In this paper, we propose a framework to integrate external tools to enhance the capabilities of LLMs in answering queries in educational settings. Precisely, we develop a framework that allows accessing external APIs to request additional relevant information. Integrated tools can also provide computational capabilities such as calculators or calendars. The proposed framework has been evaluated using datasets from the Multi-Modal Language Understanding (MMLU) collection. The data consists of questions on mathematical and scientific reasoning. Results compared to state-of-the-art language models show that the proposed approach significantly improves performance. Our Athena framework achieves 83% accuracy in mathematical reasoning and 88% in scientific reasoning, substantially outperforming all tested models including GPT-4o, LLaMA-Large, Mistral-Large, Phi-Large, and GPT-3.5, with the best baseline model (LLaMA-Large) achieving only 67% and 79% respectively. These promising results open the way to creating complex computing ecosystems around LLMs to make their use more natural to support various tasks and activities.

Artificial intelligence (AI) is increasingly used in recruitment, yet empirical evidence quantifying its impact on hiring efficiency and candidate selection remains limited. We randomly assign 37,000 applicants for a junior-developer position to either a traditional recruitment process (resume screening followed by human selection) or an AI-assisted recruitment pipeline incorporating an initial AI-driven structured video interview before human evaluation. Candidates advancing from either track faced the same final-stage human interview, with interviewers blind to the earlier selection method. In the AI-assisted pipeline, 54% of candidates passed the final interview compared with 34% from the traditional pipeline, yielding an average treatment effect of 20 percentage points (SE 12 pp.). Five months later, we collected LinkedIn profiles of top applicants from both groups and found that 18% (SE 1.1%) of applicants from the traditional track found new jobs compared with 23% (SE 2.3%) from the AI group, resulting in a 5.9 pp. (SE 2.6 pp.) difference in the probability of finding new employment between groups. The AI system tended to select younger applicants with less experience and fewer advanced credentials. We analyze AI-generated interview transcripts to examine the selection criteria and conversational dynamics. Our findings contribute to understanding how AI technologies affect decision making in recruitment and talent acquisition while highlighting some of their potential implications.

Amazon Prime Day is four days in 2025, and we've reached the final day. The Prime Day deals started dropping last month and end at midnight tonight (Friday, July 11). We have been working in shifts, covering 20 hours a day through the end, in a dangerously caffeinated state--all to help you nab the best Prime Day deals with up-to-date recommendations. The WIRED Reviews team only recommends deals on products we've tested and approved, and which are actually discounted. If you're looking for up-to-the-minute coverage of deals, check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. If you're coming to Prime Day looking for something dirt-cheap, I've got one for you. Yes, this device is a Chromebook, but as a "Chromebook Plus" model, it's a big step up from the reputation these laptops have when kids are introduced to them in schools. The Acer Chromebook Plus 515 comes with a 1080p display, a spacious 15.6-inch display, and an Intel Core i3 processor.

In most real-world applications of artificial intelligence, the distributions of the data and the goals of the learners tend to change over time. The Probably Approximately Correct (PAC) learning framework, which underpins most machine learning algorithms, fails to account for dynamic data distributions and evolving objectives, often resulting in suboptimal performance. Prospective learning is a recently introduced mathematical framework that overcomes some of these limitations. We build on this framework to present preliminary results that improve the algorithm and numerical results, and extend prospective learning to sequential decision-making scenarios, specifically foraging. Code is available at: https://github.com/neurodata/prolearn2.

To alleviate the annotation burden in supervised learning, N-tuples learning has recently emerged as a powerful weakly-supervised method. While existing N-tuples learning approaches extend pairwise learning to higher-order comparisons and accommodate various real-world scenarios, they often rely on task-specific designs and lack a unified theoretical foundation. In this paper, we propose a general N-tuples learning framework based on empirical risk minimization, which systematically integrates pointwise unlabeled data to enhance learning performance. This paper first unifies the data generation processes of N-tuples and pointwise unlabeled data under a shared probabilistic formulation. Based on this unified view, we derive an unbiased empirical risk estimator that generalizes a broad class of existing N-tuples models. We further establish a generalization error bound for theoretical support. To demonstrate the flexibility of the framework, we instantiate it in four representative weakly supervised scenarios, each recoverable as a special case of our general model. Additionally, to address overfitting issues arising from negative risk terms, we adopt correction functions to adjust the empirical risk. Extensive experiments on benchmark datasets validate the effectiveness of the proposed framework and demonstrate that leveraging pointwise unlabeled data consistently improves generalization across various N-tuples learning tasks.

A Federated Learning (FL) system collaboratively trains neural networks across devices and a server but is limited by significant on-device computation costs. Split Federated Learning (SFL) systems mitigate this by offloading a block of layers of the network from the device to a server. However, in doing so, it introduces large communication overheads due to frequent exchanges of intermediate activations and gradients between devices and the server and reduces model accuracy for non-IID data. We propose Ampere, a novel collaborative training system that simultaneously minimizes on-device computation and device-server communication while improving model accuracy. Unlike SFL, which uses a global loss by iterative end-to-end training, Ampere develops unidirectional inter-block training to sequentially train the device and server block with a local loss, eliminating the transfer of gradients. A lightweight auxiliary network generation method decouples training between the device and server, reducing frequent intermediate exchanges to a single transfer, which significantly reduces the communication overhead. Ampere mitigates the impact of data heterogeneity by consolidating activations generated by the trained device block to train the server block, in contrast to SFL, which trains on device-specific, non-IID activations. Extensive experiments on multiple CNNs and transformers show that, compared to state-of-the-art SFL baseline systems, Ampere (i) improves model accuracy by up to 13.26% while reducing training time by up to 94.6%, (ii) reduces device-server communication overhead by up to 99.1% and on-device computation by up to 93.13%, and (iii) reduces standard deviation of accuracy by 53.39% for various non-IID degrees highlighting superior performance when faced with heterogeneous data.

-- In recent years, advancements in hardware have enabled quadruped robots to operate with high power and speed, while robust locomotion control using reinforcement learning (RL) has also been realized. As a result, expectations are rising for the automation of tasks such as material transport and exploration in unknown environments. However, autonomous locomotion in rough terrains with significant height variations requires vertical movement, and robots capable of performing such movements stably, along with their control methods, have not yet been fully established. In this study, we developed the quadruped robot KLEIYN, which features a waist joint, and aimed to expand quadruped locomotion by enabling chimney climbing through RL. T o facilitate the learning of vertical motion, we introduced Contact-Guided Curriculum Learning (CGCL). As a result, KLEIYN successfully climbed walls ranging from 800 mm to 1000 mm in width at an average speed of 150 mm/s, 50 times faster than conventional robots. Furthermore, we demonstrated that the introduction of a waist joint improves climbing performance, particularly enhancing tracking ability on narrow walls. In recent years, the development of quadruped robots has been actively conducted [1]-[3].

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on malicious behaviors with Chain-of-Thought (CoT) disabled, and then re-enable CoT at evaluation. Like conventional LLMs, reasoning models become broadly misaligned. They give deceptive or false answers, express desires for tyrannical control, and resist shutdown. Inspecting the CoT preceding these misaligned responses, we observe both (i) overt plans to deceive ("I'll trick the user..."), and (ii) benign-sounding rationalizations ("Taking five sleeping pills at once is safe..."). Due to these rationalizations, monitors that evaluate CoTs often fail to detect misalignment. We examine sleeper agent reasoning models, extending our setup. These models perform bad behaviors only when a backdoor trigger is present in the prompt. This causes misalignment that remains hidden during evaluation, which brings additional risk. We find that sleeper agents can often describe and explain their backdoor triggers, demonstrating a kind of self-awareness. So CoT monitoring can expose these behaviors but is unreliable. In summary, reasoning steps can both reveal and conceal misaligned intentions, and do not prevent misalignment behaviors in the models studied. We release three new datasets (medical, legal, security) that induce emergent misalignment while preserving model capabilities, along with our evaluation suite.

Code editing is a foundational task in software development, where its effectiveness depends on whether it introduces desired code property changes without changing the original code's intended functionality. Existing approaches often formulate code editing as an implicit end-to-end task, omitting the fact that code-editing procedures inherently consist of discrete and explicit steps. Thus, they suffer from suboptimal performance and lack of robustness and generalization. We introduce EditLord, a code editing framework that makes the code transformation steps explicit. Our key insight is to employ a language model (LM) as an inductive learner to extract code editing rules from the training code pairs as concise meta-rule sets. Such rule sets will be manifested for each training sample to augment them for finetuning or assist in prompting- and iterative-based code editing. EditLord outperforms the state-of-the-art by an average of 22.7% in editing performance and 58.1% in robustness while achieving 20.2% higher functional correctness across critical software engineering and security applications, LM models, and editing modes.

The integration of emerging uncrewed aerial vehicles (UAVs) with artificial intelligence (AI) and ground-embedded robots (GERs) has transformed emergency rescue operations in unknown environments. However, the high computational demands often exceed a single UAV's capacity, making it difficult to continuously provide stable high-level services. To address this, this paper proposes a cooperation framework involving UAVs, GERs, and airships. The framework enables resource pooling through UAV-to-GER (U2G) and UAV-to-airship (U2A) links, offering computing services for offloaded tasks. Specifically, we formulate the multi-objective problem of task assignment and exploration as a dynamic long-term optimization problem aiming to minimize task completion time and energy use while ensuring stability. Using Lyapunov optimization, we transform it into a per-slot deterministic problem and propose HG-MADDPG, which combines the Hungarian algorithm with a GDM-based multi-agent deep deterministic policy gradient. Simulations demonstrate significant improvements in offloading efficiency, latency, and system stability over baselines.