The rapid advancement of artificial intelligence has raised concerns about its potential to facilitate biological weapons development. We argue existing safety assessments of contemporary foundation AI models underestimate this risk, largely due to flawed assumptions and inadequate evaluation methods. First, assessments mistakenly assume biological weapons development requires tacit knowledge, or skills gained through hands-on experience that cannot be easily verbalized. Second, they rely on imperfect benchmarks that overlook how AI can uplift both nonexperts and already-skilled individuals. To challenge the tacit knowledge assumption, we examine cases where individuals without formal expertise, including a 2011 Norwegian ultranationalist who synthesized explosives, successfully carried out complex technical tasks. We also review efforts to document pathogen construction processes, highlighting how such tasks can be conveyed in text. We identify "elements of success" for biological weapons development that large language models can describe in words, including steps such as acquiring materials and performing technical procedures. Applying this framework, we find that advanced AI models Llama 3.1 405B, ChatGPT-4o, and Claude 3.5 Sonnet can accurately guide users through the recovery of live poliovirus from commercially obtained synthetic DNA, challenging recent claims that current models pose minimal biosecurity risk. We advocate for improved benchmarks, while acknowledging the window for meaningful implementation may have already closed.

Humans interpret the world around them in terms of cause and effect and communicate their understanding of the world to each other in causal terms. These causal aspects of human cognition are thought to underlie humans' ability to generalize and learn efficiently in new domains, an area where current machine learning systems are weak. Building human-like causal competency into machine learning systems may facilitate the construction of effective and interpretable AI. Indeed, the machine learning community has been importing ideas on causality formalized by the Structural Causal Model (SCM) framework, which provides a rigorous formal language for many aspects of causality and has led to significant advances. However, the SCM framework fails to capture some salient aspects of human causal cognition and has likewise not yet led to advances in machine learning in certain critical areas where humans excel. We contend that the problem of causality in the ``human niche'' -- for a social, autonomous, and goal-driven agent sensing and acting in the world in which humans live -- is quite different from the kind of causality captured by SCMs. For example, everyday objects come in similar types that have similar causal properties, and so humans readily generalize knowledge of one type of object (cups) to another related type (bowls) by drawing causal analogies between objects with similar properties, but such analogies are at best awkward to express in SCMs. We explore how such causal capabilities are adaptive in, and motivated by, the human niche. By better appreciating properties of human causal cognition and, crucially, how those properties are adaptive in the niche in which humans live, we hope that future work at the intersection of machine learning and causality will leverage more human-like inductive biases to create more capable, controllable, and interpretable systems.

Language models today are widely used in education, yet their ability to tailor responses for learners with varied informational needs and knowledge backgrounds remains under-explored. To this end, we introduce ELI-Why, a benchmark of 13.4K "Why" questions to evaluate the pedagogical capabilities of language models. We then conduct two extensive human studies to assess the utility of language model-generated explanatory answers (explanations) on our benchmark, tailored to three distinct educational grades: elementary, high-school and graduate school. In our first study, human raters assume the role of an "educator" to assess model explanations' fit to different educational grades. We find that GPT-4-generated explanations match their intended educational background only 50% of the time, compared to 79% for lay human-curated explanations. In our second study, human raters assume the role of a learner to assess if an explanation fits their own informational needs. Across all educational backgrounds, users deemed GPT-4-generated explanations 20% less suited on average to their informational needs, when compared to explanations curated by lay people. Additionally, automated evaluation metrics reveal that explanations generated across different language model families for different informational needs remain indistinguishable in their grade-level, limiting their pedagogical effectiveness.

Cybernetic avatars are hybrid interaction robots or digital representations that combine autonomous capabilities with teleoperated control. This study investigates the acceptance of cybernetic avatars in the highly multicultural society of Dubai, with particular emphasis on robotic avatars for customer service. Specifically, we explore how acceptance varies as a function of robot appearance (e.g., android, robotic-looking, cartoonish), deployment settings (e.g., shopping malls, hotels, hospitals), and functional tasks (e.g., providing information, patrolling). To this end, we conducted a large-scale survey with over 1,000 participants. Overall, cybernetic avatars received a high level of acceptance, with physical robot avatars receiving higher acceptance than digital avatars. In terms of appearance, robot avatars with a highly anthropomorphic robotic appearance were the most accepted, followed by cartoonish designs and androids. Animal-like appearances received the lowest level of acceptance. Among the tasks, providing information and guidance was rated as the most valued. Shopping malls, airports, public transport stations, and museums were the settings with the highest acceptance, whereas healthcare-related spaces received lower levels of support. An analysis by community cluster revealed among others that Emirati respondents showed significantly greater acceptance of android appearances compared to the overall sample, while participants from the 'Other Asia' cluster were significantly more accepting of cartoonish appearances. Our study underscores the importance of incorporating citizen feedback into the design and deployment of cybernetic avatars from the early stages to enhance acceptance of this technology in society.

Reinforcement learning-based traffic signal control (RL-TSC) has emerged as a promising approach for improving urban mobility. However, its robustness under real-world disruptions such as traffic incidents remains largely underexplored. In this study, we introduce T-REX, an open-source, SUMO-based simulation framework for training and evaluating RL-TSC methods under dynamic, incident scenarios. T-REX models realistic network-level performance considering drivers' probabilistic rerouting, speed adaptation, and contextual lane-changing, enabling the simulation of congestion propagation under incidents. To assess robustness, we propose a suite of metrics that extend beyond conventional traffic efficiency measures. Through extensive experiments across synthetic and real-world networks, we showcase T-REX for the evaluation of several state-of-the-art RL-TSC methods under multiple real-world deployment paradigms. Our findings show that while independent value-based and decentralized pressure-based methods offer fast convergence and generalization in stable traffic conditions and homogeneous networks, their performance degrades sharply under incident-driven distribution shifts. In contrast, hierarchical coordination methods tend to offer more stable and adaptable performance in large-scale, irregular networks, benefiting from their structured decision-making architecture. However, this comes with the trade-off of slower convergence and higher training complexity. These findings highlight the need for robustness-aware design and evaluation in RL-TSC research. T-REX contributes to this effort by providing an open, standardized and reproducible platform for benchmarking RL methods under dynamic and disruptive traffic scenarios.

This study investigates router-based multi-agent systems for automating foundation design calculations through intelligent task classification and expert selection. Three approaches were evaluated: single-agent processing, multi-agent designer-checker architecture, and router-based expert selection. Performance assessment utilized baseline models including DeepSeek R1, ChatGPT 4 Turbo, Grok 3, and Gemini 2.5 Pro across shallow foundation and pile design scenarios. The router-based configuration achieved performance scores of 95.00% for shallow foundations and 90.63% for pile design, representing improvements of 8.75 and 3.13 percentage points over standalone Grok 3 performance respectively. The system outperformed conventional agentic workflows by 10.0 to 43.75 percentage points. Grok 3 demonstrated superior standalone performance without external computational tools, indicating advances in direct LLM mathematical reasoning for engineering applications. The dual-tier classification framework successfully distinguished foundation types, enabling appropriate analytical approaches. Results establish router-based multi-agent systems as optimal for foundation design automation while maintaining professional documentation standards. Given safety-critical requirements in civil engineering, continued human oversight remains essential, positioning these systems as advanced computational assistance tools rather than autonomous design replacements in professional practice.

Algorithm Distillation (AD) was recently proposed as a new approach to perform In-Context Reinforcement Learning (ICRL) by modeling across-episodic training histories autoregressively with a causal transformer model. However, due to practical limitations induced by the attention mechanism, experiments were bottlenecked by the transformer's quadratic complexity and limited to simple discrete environments with short time horizons. In this work, we propose leveraging the recently proposed Selective Structured State Space Sequence (S6) models, which achieved state-of-the-art (SOTA) performance on long-range sequence modeling while scaling linearly in sequence length. Through four complex and continuous Meta Reinforcement Learning environments, we demonstrate the overall superiority of Mamba, a model built with S6 layers, over a transformer model for AD. Additionally, we show that scaling AD to very long contexts can improve ICRL performance and make it competitive even with a SOTA online meta RL baseline.

Imitation learning has driven the development of generalist policies capable of autonomously solving multiple tasks. However, when a pretrained policy makes errors during deployment, there are limited mechanisms for users to correct its behavior. While collecting additional data for finetuning can address such issues, doing so for each downstream use case is inefficient at deployment. My research proposes an alternative: keeping pretrained policies frozen as a fixed skill repertoire while allowing user interactions to guide behavior generation toward user preferences at inference time. By making pretrained policies steerable, users can help correct policy errors when the model struggles to generalize-without needing to finetune the policy. Specifically, I propose (1) inference-time steering, which leverages user interactions to switch between discrete skills, and (2) task and motion imitation, which enables user interactions to edit continuous motions while satisfying task constraints defined by discrete symbolic plans. These frameworks correct misaligned policy predictions without requiring additional training, maximizing the utility of pretrained models while achieving inference-time user objectives.

Despite impressive progress on complex reasoning, current large language models (LLMs) typically operate in isolation - treating each problem as an independent attempt, without accumulating or integrating experiential knowledge. In contrast, expert problem solvers - such as Olympiad or programming contest teams - leverage a rich tapestry of experiences: absorbing mentorship from coaches, developing intuition from past problems, leveraging knowledge of tool usage and library functionality, adapting strategies based on the expertise and experiences of peers, continuously refining their reasoning through trial and error, and learning from other related problems even during competition. We introduce Xolver, a training-free multi-agent reasoning framework that equips a black-box LLM with a persistent, evolving memory of holistic experience. Xolver integrates diverse experience modalities, including external and self-retrieval, tool use, collaborative interactions, agent-driven evaluation, and iterative refinement. By learning from relevant strategies, code fragments, and abstract reasoning patterns at inference time, Xolver avoids generating solutions from scratch - marking a transition from isolated inference toward experience-aware language agents. Built on both open-weight and proprietary models, Xolver consistently outperforms specialized reasoning agents. Even with lightweight backbones (e.g., QWQ-32B), it often surpasses advanced models including Qwen3-235B, Gemini 2.5 Pro, o3, and o4-mini-high. With o3-mini-high, it achieves new best results on GSM8K (98.1%), AIME'24 (94.4%), AIME'25 (93.7%), Math-500 (99.8%), and LiveCodeBench-V5 (91.6%) - highlighting holistic experience learning as a key step toward generalist agents capable of expert-level reasoning. Code and data are available at https://kagnlp.github.io/xolver.github.io/.

The increasing availability and use of artificial intelligence (AI) tools in educational settings has raised concerns about students' overreliance on these technologies. Overreliance occurs when individuals accept incorrect AI-generated recommendations, often without critical evaluation, leading to flawed problem solutions and undermining learning outcomes. This study investigates potential factors contributing to patterns of AI reliance among undergraduate students, examining not only overreliance but also appropriate reliance (correctly accepting helpful and rejecting harmful recommendations) and underreliance (incorrectly rejecting helpful recommendations). Our approach combined pre- and post-surveys with a controlled experimental task where participants solved programming problems with an AI assistant that provided both accurate and deliberately incorrect suggestions, allowing direct observation of students' reliance patterns when faced with varying AI reliability. We find that appropriate reliance is significantly related to students' programming self-efficacy, programming literacy, and need for cognition, while showing negative correlations with post-task trust and satisfaction. Overreliance showed significant correlations with post-task trust and satisfaction with the AI assistant. Underreliance was negatively correlated with programming literacy, programming self-efficacy, and need for cognition. Overall, the findings provide insights for developing targeted interventions that promote appropriate reliance on AI tools, with implications for the integration of AI in curriculum and educational technologies.