This paper presents a theoretical framework for the AI ethical resonance hypothesis, which proposes that advanced AI systems with purposefully designed cognitive structures ("ethical resonators") may emerge with the ability to identify subtle moral patterns that are invisible to the human mind. The paper explores the possibility that by processing and synthesizing large amounts of ethical contexts, AI systems may discover moral meta-patterns that transcend cultural, historical, and individual biases, potentially leading to a deeper understanding of universal ethical foundations. The paper also examines a paradoxical aspect of the hypothesis, in which AI systems could potentially deepen our understanding of what we traditionally consider essentially human - our capacity for ethical reflection.

As cosmological simulations and their associated software become increasingly complex, physicists face the challenge of searching through vast amounts of literature and user manuals to extract simulation parameters from dense academic papers, each using different models and formats. Translating these parameters into executable scripts remains a time-consuming and error-prone process. To improve efficiency in physics research and accelerate the cosmological simulation process, we introduce SimAgents, a multi-agent system designed to automate both parameter configuration from the literature and preliminary analysis for cosmology research. SimAgents is powered by specialized LLM agents capable of physics reasoning, simulation software validation, and tool execution. These agents collaborate through structured communication, ensuring that extracted parameters are physically meaningful, internally consistent, and software-compliant. We also construct a cosmological parameter extraction evaluation dataset by collecting over 40 simulations in published papers from Arxiv and leading journals that cover diverse simulation types. Experiments on the dataset demonstrate a strong performance of SimAgents, highlighting its effectiveness and potential to accelerate scientific research for physicists. Our demonstration video is available at: https://youtu.be/w1zLpm_CaWA. The complete system and dataset are publicly available at https://github.com/xwzhang98/SimAgents.

Traditional agent-based urban mobility simulations often rely on rigid rule-based systems that struggle to capture the complexity, adaptability, and behavioral diversity inherent in human travel decision making. Recent advancements in large language models and AI agent technologies present new opportunities to develop agents with enhanced reasoning capabilities, persistent memory, and adaptive learning. We introduce GATSim (Generative-Agent Transport Simulation), a novel framework that leverages these advancements to simulate urban mobility using generative agents with rich, human-like behaviors. Unlike conventional approaches, GATSim agents are characterized by diverse socioeconomic profiles, individual lifestyles, and evolving preferences shaped through psychologically informed memory systems, tool usage, and lifelong learning. The main contributions of this work are: (1) a comprehensive architecture that integrates an urban mobility foundation model with agent cognitive systems and a transport simulation environment; (2) a hierarchical memory designed for efficient retrieval of contextually relevant information, incorporating spatial and temporal associations, keyword matching, and semantic relevance; (3) innovative planning and reactive mechanisms for modeling adaptive mobility behaviors which integrate a multi-scale reflection process to transform specific travel experiences into generalized behavioral insights. We implement a prototype system and conduct systematic validation, demonstrating that generative agents produce believable and coherent travel behaviors. Experimental results indicate that generative agents perform at least as well as human annotators with 92\% posterior probability, while naturally producing realistic macroscopic traffic patterns. The code for the prototype implementation is publicly available at https://github.com/qiliuchn/gatsim.

Agents based on Large Language Models (LLMs) have shown promise for performing sophisticated software engineering tasks autonomously. In addition, there has been progress towards developing agents that can perform parts of the research pipeline in machine learning and the natural sciences. We argue that research extension and its implementation is a critical capability for such systems, and introduce RExBench to support the evaluation of this capability. RExBench is a benchmark consisting of 12 realistic research experiment implementation tasks that aim to investigate research hypotheses that have not previously been implemented. Each task is set up as an extension to an existing research paper and codebase, accompanied by domain expert-written instructions. RExBench is robust to data contamination, and supports an automatic evaluation infrastructure that executes agent outputs to determine whether the success criteria are met. We use this benchmark to evaluate nine LLM agents implemented using three different frameworks: aider, Claude Code, and OpenHands. We find that all agents evaluated fail to autonomously implement the majority of the extensions. Although the success rate improves with additional human-written hints, the best performance under this setting remains below 40%. This indicates that current agents are still short of being able to handle realistic research extension tasks without substantial human guidance.

Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network(ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative "team" focused on a specific subtask. Agentic Neural Network follows a two-phase optimization strategy: (1) Forward Phase-Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer. (2) Backward Phase-Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination. This neuro-symbolic approach enables ANN to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability. Across four benchmark datasets, ANN surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. Our findings indicate that ANN provides a scalable, data-driven framework for multi-agent systems, combining the collaborative capabilities of LLMs with the efficiency and flexibility of neural network principles. We plan to open-source the entire framework.

Multi-agent systems built on language models have shown strong performance on collaborative reasoning tasks. However, existing evaluations focus only on the correctness of the final output, overlooking how inefficient communication and poor coordination contribute to redundant reasoning and higher computational costs. We introduce GEMMAS, a graph-based evaluation framework that analyzes the internal collaboration process by modeling agent interactions as a directed acyclic graph. To capture collaboration quality, we propose two process-level metrics: Information Diversity Score (IDS) to measure semantic variation in inter-agent messages, and Unnecessary Path Ratio (UPR) to quantify redundant reasoning paths. We evaluate GEMMAS across five benchmarks and highlight results on GSM8K, where systems with only a 2.1% difference in accuracy differ by 12.8% in IDS and 80% in UPR, revealing substantial variation in internal collaboration. These findings demonstrate that outcome-only metrics are insufficient for evaluating multi-agent performance and highlight the importance of process-level diagnostics in designing more interpretable and resource-efficient collaborative AI systems.

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly disclosed to OpenAI. Over the last three years, these attacks have remained a critical security threat for LLM-integrated systems. The emergence of agentic AI systems, where LLMs autonomously perform multistep tasks through tools and coordination with other agents, has fundamentally transformed the threat landscape. Modern prompt injection attacks can now combine with traditional cybersecurity exploits to create hybrid threats that systematically evade traditional security controls, but also, like in the case of academic peer reviews, raise serious ethical concerns. This paper presents a comprehensive analysis of Prompt Injection 2.0, examining how prompt injections integrate with Cross-Site Scripting (XSS), Cross-Site Request Forgery (CSRF), and other web security vulnerabilities to bypass traditional security measures. We build upon Preamble's research and mitigation technologies, evaluating them against contemporary threats, including AI worms, multi-agent infections, and hybrid cyber-AI attacks. Our analysis incorporates recent benchmarks that demonstrate how traditional web application firewalls, XSS filters, and CSRF tokens fail against AI-enhanced attacks. We also present architectural solutions that combine prompt isolation, runtime security, and privilege separation with novel threat detection capabilities.

We study the power of (competitive) algorithms with predictions in a multiagent setting. We introduce a two predictor framework, that assumes that agents use one predictor for their future (self) behavior, and one for the behavior of the other players. The main problem we are concerned with is understanding what are the best competitive ratios that can be achieved by employing such predictors, under various assumptions on predictor quality. As an illustration of our framework, we introduce and analyze a multiagent version of the ski-rental problem. In this problem agents can collaborate by pooling resources to get a group license for some asset. If the license price is not met then agents have to rent the asset individually for the day at a unit price. Otherwise the license becomes available forever to everyone at no extra cost. In the particular case of perfect other predictions the algorithm that follows the self predictor is optimal but not robust to mispredictions of agent's future behavior; we give an algorithm with better robustness properties and benchmark it.

Safe and effective motion planning is crucial for autonomous robots. Diffusion models excel at capturing complex agent interactions, a fundamental aspect of decision-making in dynamic environments. Recent studies have successfully applied diffusion models to motion planning, demonstrating their competence in handling complex scenarios and accurately predicting multi-modal future trajectories. Despite their effectiveness, diffusion models have limitations in training objectives, as they approximate data distributions rather than explicitly capturing the underlying decision-making dynamics. However, the crux of motion planning lies in non-differentiable downstream objectives, such as safety (collision avoidance) and effectiveness (goal-reaching), which conventional learning algorithms cannot directly optimize. In this paper, we propose a reinforcement learning-based training scheme for diffusion motion planning models, enabling them to effectively learn non-differentiable objectives that explicitly measure safety and effectiveness. Specifically, we introduce a reward-weighted dynamic thresholding algorithm to shape a dense reward signal, facilitating more effective training and outperforming models trained with differentiable objectives. State-of-the-art performance on pedestrian datasets (CrowdNav, ETH-UCY) compared to various baselines demonstrates the versatility of our approach for safe and effective motion planning.

In recent years, peer learning has gained attention as a method that promotes spontaneous thinking among learners, and its effectiveness has been confirmed by numerous studies. This study aims to develop an AI Agent as a learning companion that enables peer learning anytime and anywhere. However, peer learning between humans has various limitations, and it is not always effective. Effective peer learning requires companions at the same proficiency levels. In this study, we assume that a learner's peers with the same proficiency level as the learner make the same mistakes as the learner does and focus on English composition as a specific example to validate this approach.