Scientists have identified more than fifty ways that houses can ignite. It's possible to defend against all of them--but it's arduous, and homeowners can't do it alone. In June, 2012, hundreds of homes in Mountain Shadows, Colorado, a subdivision in the foothills of the Rockies, were reduced to ash during the wind-whipped Waldo Canyon Fire. On a cul-de-sac called Hot Springs Court, however, four dwellings somehow remained standing. The mystery of their survival nagged at Alex Maranghides, a fire-protection engineer at the National Institute of Standards and Technology (), who worked with several colleagues on a meticulous reconstruction of the fire. How did the homes make it through? Was there something special about them--a fireproof roof, say, or a fancy sprinkler system? The team collected weather reports, topographic data, G.P.S. records from fire engines, photos, videos, and property-damage reports.

Recent advances in Large Language Models (LLMs) have been driven by test-time compute scaling - a strategy that improves reasoning by generating longer, sequential thought processes. While effective, this approach encounters a significant bottleneck as computation increases, where further computation offers only marginal performance gains. We argue this ceiling is not an inherent limit of the model's capability but a flaw in the scaling strategy itself, a phenomenon we term "Tunnel Vision", where a model's imperfect initial steps lock it into a suboptimal reasoning path. To overcome this, we introduce a new scaling paradigm: native thought parallelism. We present ParaThinker, an end-to-end framework that trains an LLM to generate multiple, diverse reasoning paths in parallel and synthesize them into a superior final answer. By exploring different lines of thoughts simultaneously, ParaThinker effectively sidesteps the Tunnel Vision issue and unlocks the model's latent reasoning potential. Our approach demonstrates that scaling compute in parallel (width) is a more effective and efficient way to superior reasoning than simply scaling sequentially (depth). On challenging reasoning benchmarks, ParaThinker achieves substantial accuracy improvements over sequential LLMs (12.3% for 1.5B and 7.5% for 7B models on average with 8 parallel paths), while adding only negligible latency overhead (7.1%). This enables smaller models to surpass much larger counterparts and establishes parallel thinking as a critical, efficient dimension for scaling future LLMs.

Active feature acquisition (AFA) is an instance-adaptive paradigm in which, at test time, a policy sequentially chooses which features to acquire (at a cost) before predicting. Existing approaches either train reinforcement learning (RL) policies, which deal with a difficult MDP, or greedy policies that cannot account for the joint informativeness of features or require knowledge about the underlying data distribution. To overcome this, we propose Template-based AFA (TAFA), a non-greedy framework that learns a small library of feature templates--a set of features that are jointly informative--and uses this library of templates to guide the next feature acquisitions. Through identifying feature templates, the proposed framework not only significantly reduces the action space considered by the policy but also alleviates the need to estimate the underlying data distribution. Extensive experiments on synthetic and real-world datasets show that TAFA outperforms the existing state-of-the-art baselines while achieving lower overall acquisition cost and computation.

Traditional sparse and dense retrieval methods struggle to leverage general world knowledge and often fail to capture the nuanced features of queries and products. With the advent of large language models (LLMs), industrial search systems have started to employ LLMs to generate identifiers for product retrieval. Commonly used identifiers include (1) static/semantic IDs and (2) product term sets. The first approach requires creating a product ID system from scratch, missing out on the world knowledge embedded within LLMs. While the second approach leverages this general knowledge, the significant difference in word distribution between queries and products means that product-based identifiers often do not align well with user search queries, leading to missed product recalls. Furthermore, when queries contain numerous attributes, these algorithms generate a large number of identifiers, making it difficult to assess their quality, which results in low overall recall efficiency. To address these challenges, this paper introduces a novel e-commerce retrieval paradigm: the Generative Retrieval and Alignment Model (GRAM). GRAM employs joint training on text information from both queries and products to generate shared text identifier codes, effectively bridging the gap between queries and products. This approach not only enhances the connection between queries and products but also improves inference efficiency. The model uses a co-alignment strategy to generate codes optimized for maximizing retrieval efficiency. Additionally, it introduces a query-product scoring mechanism to compare product values across different codes, further boosting retrieval efficiency. Extensive offline and online A/B testing demonstrates that GRAM significantly outperforms traditional models and the latest generative retrieval models, confirming its effectiveness and practicality.

The capabilities of Large Language Models (LLMs) have opened new frontiers for interacting with complex, domain-specific knowledge. RAG provides factual context but fails to convey logical frameworks; autonomous agents can be inefficient and unpredictable without domain-specific heuristics. To bridge this gap, we introduce Knowledge Protocol Engineering (KPE), a new paradigm focused on systematically translating human expert knowledge, often expressed in natural language documents, into a machine-executable Knowledge Protocol (KP) . KPE shifts the focus from merely augmenting LLMs with fragmented information to endowing them with a domain's intrinsic logic, operational strategies, and methodological principles. We argue that a well-engineered Knowledge Protocol allows a generalist LLM to function as a specialist, capable of decomposing abstract queries and executing complex, multi-step tasks. This position paper defines the core principles of KPE, differentiates it from related concepts, and illustrates its potential applicability across diverse fields such as law and bioinformatics, positing it as a foundational methodology for the future of human-AI collaboration.

White House press secretary Karoline Leavitt answers questions on U.S. strikes on Iran amid an intelligence leak about the operation. FIRST ON FOX: A group of House Republicans is demanding to know how the U.S. is ready to protect its own domestic assets in the event of a potential attack on the homeland. "We write to inquire with the U.S. Department of Defense (DOD) and the Department of Homeland Security (DHS) about the current state of drone attack countermeasures for our military installations, government buildings, embassies, and consulates, both domestic and abroad," the GOP lawmakers wrote in a letter. "The ongoing conflicts in Ukraine and the Middle East have demonstrated that large-scale, highly coordinated mass-drone attacks can be highly effective if the defender lacks adequate counter-drone defenses." An Iranian demonstrator holds an anti-American sign.

Deep Reinforcement Learning (DRL) agents often exhibit intricate failure modes that are difficult to understand, debug, and learn from. This opacity hinders their reliable deployment in real-world applications. To address this critical gap, we introduce ``Ghost Policies,'' a concept materialized through Arvolution, a novel Augmented Reality (AR) framework. Arvolution renders an agent's historical failed policy trajectories as semi-transparent ``ghosts'' that coexist spatially and temporally with the active agent, enabling an intuitive visualization of policy divergence. Arvolution uniquely integrates: (1) AR visualization of ghost policies, (2) a behavioural taxonomy of DRL maladaptation, (3) a protocol for systematic human disruption to scientifically study failure, and (4) a dual-learning loop where both humans and agents learn from these visualized failures. We propose a paradigm shift, transforming DRL agent failures from opaque, costly errors into invaluable, actionable learning resources, laying the groundwork for a new research field: ``Failure Visualization Learning.''

The predominant de facto paradigm of testing ML models relies on either using only held-out data to compute aggregate evaluation metrics or by assessing the performance on different subgroups. However, such data-only testing methods operate under the restrictive assumption that the available empirical data is the sole input for testing ML models, disregarding valuable contextual information that could guide model testing. In this paper, we challenge the go-to approach of data-only testing and introduce Context-Aware Testing (CAT) which uses context as an inductive bias to guide the search for meaningful model failures. We instantiate the first CAT system, SMART Testing, which employs large language models to hypothesize relevant and likely failures, which are evaluated on data using a self-falsification mechanism. Through empirical evaluations in diverse settings, we show that SMART automatically identifies more relevant and impactful failures than alternatives, demonstrating the potential of CAT as a testing paradigm.

Learned Index Structures (LIS) have significantly advanced data management by leveraging machine learning models to optimize data indexing. However, designing these structures often involves critical trade-offs, making it challenging for both designers and end-users to find an optimal balance tailored to specific workloads and scenarios. While some indexes offer adjustable parameters that demand intensive manual tuning, others rely on fixed configurations based on heuristic auto-tuners or expert knowledge, which may not consistently deliver optimal performance. This paper introduces LITune, a novel framework for end-to-end automatic tuning of Learned Index Structures. LITune employs an adaptive training pipeline equipped with a tailor-made Deep Reinforcement Learning (DRL) approach to ensure stable and efficient tuning. To accommodate long-term dynamics arising from online tuning, we further enhance LITune with an on-the-fly updating mechanism termed the O2 system. These innovations allow LITune to effectively capture state transitions in online tuning scenarios and dynamically adjust to changing data distributions and workloads, marking a significant improvement over other tuning methods. Our experimental results demonstrate that LITune achieves up to a 98% reduction in runtime and a 17-fold increase in throughput compared to default parameter settings given a selected Learned Index instance. These findings highlight LITune's effectiveness and its potential to facilitate broader adoption of LIS in real-world applications.

OpenAI made the last big breakthrough in artificial intelligence by increasing the size of its models to dizzying proportions, when it introduced GPT-4 last year. The company today announced a new advance that signals a shift in approach--a model that can "reason" logically through many difficult problems and is significantly smarter than existing AI without a major scale-up. The new model, dubbed OpenAI-o1, can solve problems that stump existing AI models, including OpenAI's most powerful existing model, GPT-4o. Rather than summon up an answer in one step, as a large language model normally does, it reasons through the problem, effectively thinking out loud as a person might, before arriving at the right result. "This is what we consider the new paradigm in these models," Mira Murati, OpenAI's chief technology officer, tells WIRED.