AI that can accelerate research could drive a century of technological progress over just a few years. During such a period, new technological or political developments will raise consequential and hard-to-reverse decisions, in rapid succession. We call these developments grand challenges. These challenges include new weapons of mass destruction, AI-enabled autocracies, races to grab offworld resources, and digital beings worthy of moral consideration, as well as opportunities to dramatically improve quality of life and collective decision-making. We argue that these challenges cannot always be delegated to future AI systems, and suggest things we can do today to meaningfully improve our prospects. AGI preparedness is therefore not just about ensuring that advanced AI systems are aligned: we should be preparing, now, for the disorienting range of developments an intelligence explosion would bring.

Multimodal time series forecasting is foundational in various fields, such as utilizing satellite imagery and numerical data for predicting typhoons in climate science. However, existing multimodal approaches primarily focus on utilizing text data to help time series forecasting, leaving the visual data in existing time series datasets untouched. Furthermore, it is challenging for models to effectively capture the physical information embedded in visual data, such as satellite imagery's temporal and geospatial context, which extends beyond images themselves. To address this gap, we propose physics-informed positional e ncoding ( PIPE), a lightweight method that embeds physical information into vision language models (VLMs). PIPE introduces two key innovations: (1) a physics-informed positional indexing scheme for mapping physics to positional IDs, and (2) a variant-frequency positional encoding mechanism for encoding frequency information of physical variables and sequential order of tokens within the embedding space. By preserving both the physical information and sequential order information, PIPE significantly improves multimodal alignment and forecasting accuracy. Through the experiments on the most representative and the largest open-sourced satellite image dataset, PIPE achieves state-of-the-art performance in both deep learning forecasting and climate domain methods, demonstrating superiority across benchmarks, including a 12% improvement in typhoon intensity forecasting over prior works. Our code is provided in the supplementary material.

Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability, weighting contributions by model reliability. For misaligned models, a targeted embedding-optimization procedure fine-tunes token embeddings for moral philosophical theories, minimizing JS divergence to the consensus while preserving semantic integrity. Experiments on a large-scale social moral dilemma dataset show our approach builds robust consensus and improves individual model fidelity. These findings highlight the value of data-driven moral alignment across multiple models and its potential for safer, more consistent AI systems.

Goal-oriented proactive dialogue systems are designed to guide user conversations seamlessly towards specific objectives by planning a goal-oriented path. However, previous research has focused predominantly on optimizing these paths while neglecting the inconsistencies that may arise between generated responses and dialogue contexts, including user profiles, dialogue history, domain knowledge, and subgoals. To address this issue, we introduce a model-agnostic two-stage Consistency Reflection and Correction (CRC) framework. Specifically, in the consistency reflection stage, the model is prompted to reflect on the discrepancies between generated responses and dialogue contexts, identifying inconsistencies and suggesting possible corrections. In the consistency correction stage, the model generates responses that are more consistent with the dialogue context based on these reflection results. We conducted experiments on various model architectures with different parameter sizes, including encoder-decoder models (BART, T5) and decoder-only models (GPT-2, DialoGPT, Phi3, Mistral and LLaMA3), and the experimental results on three datasets demonstrate that our CRC framework significantly improves the consistency between generated responses and dialogue contexts.

--Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets, which existing manual or automated bug insertion methods fail to reliably produce. We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline leveraging Large Language Models (LLMs) to systematically generate, insert, and validate realistic functional bugs in RTL. BugGen partitions modules, selects mutation targets via a closed-loop agentic architecture, and employs iterative refinement and rollback mechanisms to ensure syntactic correctness and functional detectability. Evaluated across five OpenTitan IP blocks, BugGen produced 500 unique bugs with 94% functional accuracy and achieved a throughput of 17.7 validated bugs per hour--over five times faster than typical manual expert insertion. Additionally, BugGen identified 104 previously undetected bugs in Open-Titan regressions, highlighting its utility in exposing verification coverage gaps. Compared against Certitude, BugGen demonstrated over twice the syntactic accuracy, deeper exposure of testbench blind spots, and more functionally meaningful and complex bug scenarios. Furthermore, when these BugGen-generated datasets were employed to train MLbased failure triage models, we achieved high classification accuracy (88.1%-93.2%) BugGen thus provides a scalable solution for generating high-quality bug datasets, significantly enhancing verification efficiency and ML-assisted debugging. Modern hardware systems continue to grow in complexity, often incorporating billions of transistors on a single chip. This increased complexity significantly expands the scope and difficulty of design verification tasks. V erification efforts already consume more than half of the total hardware development time [1], with this fraction steadily increasing each year. The heightened complexity also results in large volumes of test failures, particularly during early front-end development and initial volume regressions, placing severe demands on debugging resources to pinpoint root causes or effectively triage these failures.

Recent advances in large reasoning models have enabled complex, step-by-step reasoning but often introduce significant overthinking, resulting in verbose and redundant outputs that hinder efficiency. In this study, we examine whether explicit self-reflection, signaled by tokens such as "Wait" and "Hmm", is necessary for advanced reasoning. We propose NoWait, a simple yet effective approach that disables explicit self-reflection by suppressing these tokens during inference. Extensive experiments on ten benchmarks across textual, visual, and video reasoning tasks show that NoWait reduces chain-of-thought trajectory length by up to 27%-51% in five R1-style model series, without compromising model utility. NoWait thus offers a plug-and-play solution for efficient and utility-preserving multimodal reasoning.

Large Language Model (LLM)-based agents have demonstrated the ability to improve performance in chemistry-related tasks by selecting appropriate tools. However, their effectiveness remains limited by the inherent prediction errors of chemistry tools. In this paper, we take a step further by exploring how LLMbased agents can, in turn, be leveraged to reduce prediction errors of the tools. To this end, we propose ChemHAS (Chemical Hierarchical Agent Stacking), a simple yet effective method that enhances chemistry tools through optimizing agent-stacking structures from limited data. ChemHAS achieves state-of-the-art performance across four fundamental chemistry tasks, demonstrating that our method can effectively compensate for prediction errors of the tools. Furthermore, we identify and characterize four distinct agent-stacking behaviors, potentially improving interpretability and revealing new possibilities for AI agent applications in scientific research. Our code and dataset are publicly available at https: //anonymous.4open.science/r/ChemHAS-01E4/README.md.

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data training or data-driven activations to identify key attention heads. However, these approaches inherently introduce data dependency, which hinders generalization and reusability. To address this issue and enhance model alignment efficiency, we propose the Attention Localization and Pruning Strategy (ALPS), an efficient algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs. Experimental results demonstrate that our method activates only 10% of attention parameters during fine-tuning while achieving a 2% performance improvement over baselines on three tasks. Moreover, the identified task-specific heads are transferable across datasets and mitigate knowledge forgetting. Our work and findings provide a novel perspective on efficient LLM alignment. The code is available at https://github.com/VoiceBeer/ALPS.

To keep pace with the increasing pace of large language models (LLM) development, model output evaluation has transitioned away from time-consuming human evaluation to automatic evaluation, where LLMs themselves are tasked with assessing and critiquing other model outputs. LLM-as-judge models are a class of generative evaluators that excel in evaluating relatively simple domains, like chat quality, but struggle in reasoning intensive domains where model responses contain more substantive and challenging content. To remedy existing judge shortcomings, we explore training judges with reinforcement learning (RL). We make three key contributions: (1) We propose the Equivalent Initial State Group Relative Policy Optimization (EIS-GRPO) algorithm, which allows us to train our judge to be robust to positional biases that arise in more complex evaluation settings. (2) We introduce ReasoningJudgeBench, a benchmark that evaluates judges in diverse reasoning settings not covered by prior work. (3) We train Judge for Reasoning (J4R), a 7B judge trained with EIS-GRPO that outperforms GPT-4o and the next best small judge by 6.7% and 9%, matching or exceeding the performance of larger GRPO-trained judges on both JudgeBench and ReasoningJudgeBench.

General-purpose large language models demonstrate notable capabilities in language comprehension and generation, achieving results that are comparable to, or even surpass, human performance in many natural language processing tasks. Nevertheless, when general models are applied to some specific domains, e.g., Classical Chinese texts, their effectiveness is often unsatisfactory, and fine-tuning open-source foundational models similarly struggles to adequately incorporate domain-specific knowledge. To address this challenge, this study developed a large language model, AI Taiyan, specifically designed for understanding and generating Classical Chinese. Experiments show that with a reasonable model design, data processing, foundational training, and fine-tuning, satisfactory results can be achieved with only 1.8 billion parameters. In key tasks related to language processing of Classical Chinese such as punctuation, identification of allusions, explanation of word meanings, and translation between ancient and modern Chinese, this model exhibits a clear advantage over both general-purpose large models and domain-specific traditional models, achieving levels close to or surpassing human baselines. This research provides a reference for the efficient construction of specialized domain-specific large language models. Furthermore, the paper discusses the application of this model in fields such as the collation of ancient texts, dictionary editing, and language research, combined with case studies.