In multi-agent deep reinforcement learning (MADRL), agents can communicate with one another to perform a task in a coordinated manner. When multiple tasks are involved, agents can also leverage knowledge from one task to improve learning in other tasks. In this paper, we propose Multi-task Communication Skills (MCS), a MADRL with communication method that learns and performs multiple tasks simultaneously, with agents interacting through learnable communication protocols. MCS employs a Transformer encoder to encode task-specific observations into a shared message space, capturing shared communication skills among agents. To enhance coordination among agents, we introduce a prediction network that correlates messages with the actions of sender agents in each task. We adapt three multi-agent benchmark environments to multi-task settings, where the number of agents as well as the observation and action spaces vary across tasks. Experimental results demonstrate that MCS achieves better performance than multi-task MADRL baselines without communication, as well as single-task MADRL baselines with and without communication.

Global digital platforms are software systems designed to serve entire populations, with some already serving billions of people. We propose atomic transactions-based multiagent transition systems and protocols as a formal framework to study them; introduce essential agents -- minimal sets of agents the removal of which makes communication impossible; and show that the cardinality of essential agents partitions all global platforms into four classes: 1. Centralised -- one (the server) 2. Decentralised -- finite $>1$ (bootstrap nodes) 3. Federated -- infinite but not universal (all servers) 4. Grassroots -- universal (all agents) Our illustrative formal example is a global social network, for which we provide centralised, decentralised, federated, and grassroots specifications via multiagent atomic transactions, and prove they all satisfy the same basic correctness properties. We discuss informally additional global platforms -- currencies, ``sharing economy'' apps, AI, and more. While this may be the first characterisation of centralised, decentralised, and federated global platforms, grassroots platforms have been formally defined previously, but using different notions. Here, we prove that their original definition implies that all agents are essential, placing grassroots platforms in a distinct class within the broader formal context that includes all global platforms. This work provides the first mathematical framework for classifying any global platform -- existing or imagined -- by providing a multiagent atomic-transactions specification of it and determining the cardinality of the minimal set of essential agents in the ensuing multiagent protocol. It thus provides a unifying mathematical approach for the study of global digital platforms, perhaps the most important class of computer systems today.

While the possibility of reaching human-like Artificial Intelligence (AI) remains controversial, the likelihood that the future will be characterized by a society with a growing presence of autonomous machines is high. Autonomous AI agents are already deployed and active across several industries and digital environments and alongside human-human and human-machine interactions, machine-machine interactions are poised to become increasingly prevalent. Given these developments, I argue that criminology must begin to address the implications of this transition for crime and social control. Drawing on Actor-Network Theory and Woolgar's decades-old call for a sociology of machines -- frameworks that acquire renewed relevance with the rise of generative AI agents -- I contend that criminologists should move beyond conceiving AI solely as a tool. Instead, AI agents should be recognized as entities with agency encompassing computational, social, and legal dimensions. Building on the literature on AI safety, I thus examine the risks associated with the rise of multi-agent AI systems, proposing a dual taxonomy to characterize the channels through which interactions among AI agents may generate deviant, unlawful, or criminal outcomes. I then advance and discuss four key questions that warrant theoretical and empirical attention: (1) Can we assume that machines will simply mimic humans? (2) Will crime theories developed for humans suffice to explain deviant or criminal behaviors emerging from interactions between autonomous AI agents? (3) What types of criminal behaviors will be affected first? (4) How might this unprecedented societal shift impact policing? These questions underscore the urgent need for criminologists to theoretically and empirically engage with the implications of multi-agent AI systems for the study of crime and play a more active role in debates on AI safety and governance.

Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a conversational platform that integrates the natural-language fluency of open-source large language models (LLMs) with real-time, parameterized access to authoritative oceanographic data streams hosted by the National Oceanic and Atmospheric Administration (NOAA). Each query such as "What was Boston Harbor's highest water level in 2024?" triggers real-time API calls that identify, parse, and synthesize relevant datasets into reproducible natural-language responses and data visualizations. In a blind comparison with three widely used AI chat-interface products, only OceanAI produced NOAA-sourced values with original data references; others either declined to answer or provided unsupported results. Designed for extensibility, OceanAI connects to multiple NOAA data products and variables, supporting applications in marine hazard forecasting, ecosystem assessment, and water-quality monitoring. By grounding outputs and verifiable observations, OceanAI advances transparency, reproducibility, and trust, offering a scalable framework for AI-enabled decision support within the oceans. A public demonstration is available at https://oceanai.ai4ocean.xyz.

Abstract-- We study the robustness of an agent decision-making model in finite-population games, with a particular focus on the Kullback-Leibler Divergence Regularized Learning (KLD-RL) model. Specifically, we examine how the model's parameters influence the impact of various sources of noise and modeling inaccuracies--factors commonly encountered in engineering applications of population games--on agents' decision-making. Our analysis provides insights into how these parameters can be effectively tuned to mitigate such effects. Theoretical results are supported by numerical examples and simulation studies that validate the analysis and illustrate practical strategies for parameter selection. The population game and evolutionary dynamics framework provides a powerful foundation for modeling and analyzing repeated strategic interactions among a population of decision-making agents [1].

Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development and the persistent challenges faced by its developers, has received little attention in APR research. In this paper, we introduce RAMP, a novel lightweight framework that formulates program repair as a feedback-driven, iterative process for Ruby. RAMP employs a team of collaborative agents that generate targeted tests, reflect on errors, and refine candidate fixes until a correct solution is found. Unlike prior approaches, RAMP is designed to avoid reliance on large multilingual repair databases or costly fine-tuning, instead operating directly on Ruby through lightweight prompting and test-driven feedback. Evaluation on the XCodeEval benchmark shows that RAMP achieves a pass@1 of 67% on Ruby, outper-forming prior approaches. RAMP converges quickly within five iterations, and ablation studies confirm that test generation and self-reflection are key drivers of its performance. Further analysis shows that RAMP is particularly effective at repairing wrong answers, compilation errors, and runtime errors. Our approach provides new insights into multi-agent repair strategies, and establishes a foundation for extending LLM-based debugging tools to under-studied languages.

Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing optimization methods, however, rely on time-consuming manual tuning or resource-intensive black-box searches, which struggle to keep pace with the rapidly evolving LLM domain, leading to slow development and underutilized resources. To address this, we introduce ASAP, an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training. It is a multi-agent system, featuring Coordinator, Analyzer, and Proposal agents, which integrates LLM reasoning with insights from performance profiling tools, roofline analysis, and a knowledge base of best practices and successful past optimizations from human experts. Our proposed design can automate the diagnosis of performance bottlenecks and recommend optimized sharding configurations with reasoning, thus effectively improving the efficiency of distributed LLM training. Experiments have shown that the ASAP-generated sharding configurations can contribute up to 28% training step time reduction and 1.43 times throughput improvement. When combined with additional optimization from human experts, throughput can be further increased to 2.58 times. The proposed ASAP promises to provide a scalable and explainable methodology for AI-assisted performance engineering in large-scale LLM training.

Explainable Artificial Intelligence (XAI) aims to create transparency in modern AI models by offering explanations of the models to human users. There are many ways in which researchers have attempted to evaluate the quality of these XAI models, such as user studies or proposed objective metrics like "fidelity". However, these current XAI evaluation techniques are ad hoc at best and not generalizable. Thus, most studies done within this field conduct simple user surveys to analyze the difference between no explanations and those generated by their proposed solution. We do not find this to provide adequate evidence that the explanations generated are of good quality since we believe any kind of explanation will be "better" in most metrics when compared to none at all. Thus, our study looks to highlight this pitfall: most explanations, regardless of quality or correctness, will increase user satisfaction. We also propose that emphasis should be placed on actionable explanations. We demonstrate the validity of both of our claims using an agent assistant to teach chess concepts to users. The results of this chapter will act as a call to action in the field of XAI for more comprehensive evaluation techniques for future research in order to prove explanation quality beyond user satisfaction. Additionally, we present an analysis of the scenarios in which placebic or actionable explanations would be most useful.

The AI Song Contest was founded with the aim of showcasing the potential of human-AI co-creativity in the songwriting process. Now in its sixth year, the competition will conclude on 16 November with a live show in Amsterdam. From all the entrants, the jury have selected their top ten songs. The live event will feature performances from the ten finalists, and you will be able to watch on YouTube here . Listen to the songs and vote for your favourite.

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and Executors. In practice, training entire stacks end-to-end remains impractical, so most work trains a single planner connected to core tools such as search, browsing, and code. While SFT imparts protocol fidelity, it suffers from imitation and exposure biases and underuses environment feedback. Preference alignment methods such as DPO are schema and proxy-dependent, off-policy, and weak for long-horizon credit assignment and multi-objective trade-offs. A further limitation of SFT and DPO is their reliance on human defined decision points and subskills through schema design and labeled comparisons. Reinforcement learning aligns with closed-loop, tool-interaction research by optimizing trajectory-level policies, enabling exploration, recovery behaviors, and principled credit assignment, and it reduces dependence on such human priors and rater biases. This survey is, to our knowledge, the first dedicated to the RL foundations of deep research systems. It systematizes recent work along three axes: (i) data synthesis and curation; (ii) RL methods for agentic research covering stability, sample efficiency, long context handling, reward and credit design, multi-objective optimization, and multimodal integration; and (iii) agentic RL training systems and frameworks. We also cover agent architecture and coordination, as well as evaluation and benchmarks, including recent QA, VQA, long-form synthesis, and domain-grounded, tool-interaction tasks. We distill recurring patterns, surface infrastructure bottlenecks, and offer practical guidance for training robust, transparent deep research agents with RL.