As the Group of 20 leaders gather in Cape Town, clean air features on the agenda as a standalone priority for the first time in the forum's history. The reality, however, is stark. Outdoor air pollution claims 5.7 million lives each year, and a report released last week highlights the lack of international development finance for clean air. Only $3.7bn was spent globally in 2023, representing barely 1 percent of aid, with only a fraction reaching Africa. As the minister chairing the G20's environment workstream this year, I am proud to have worked with member countries and international organisations to place air pollution firmly on the agenda.

Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and healthcare outcomes. While Large Language Models (LLMs) have shown promising results in various domains, their practical application in industry-relevant operations research (OR) problems presents significant challenges and opportunities. Preliminary industrial applications of LLMs for operations research face two critical deployment challenges: 1) Self-correction focuses on code syntax rather than mathematical accuracy, causing costly errors; 2) Complex expert selection creates unpredictable workflows that reduce transparency and increase maintenance costs, making them impractical for time-sensitive business applications. To address these business limitations, we introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning. Our approach emulates human cognition, implementing an end-to-end workflow that systematically transforms requirements into mathematical models and executable solver code. It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers. Experiments demonstrate that ORMind outperforms existing methods, achieving a 9.5\% improvement on the NL4Opt dataset and a 14.6\% improvement on the ComplexOR dataset.

Modern consumer banking applications require accurate and efficient retrieval of information in response to user queries. Mapping user utterances to the most relevant Frequently Asked Questions (FAQs) is a crucial component of these systems. Traditional approaches often rely on a single model or technique, which may not capture the nuances of diverse user inquiries. In this paper, we introduce a multi-agent framework for FAQ annotation that combines multiple specialized agents with different approaches and a judge agent that reranks candidates to produce optimal results. Our agents utilize a structured reasoning approach inspired by Attentive Reasoning Queries (ARQs), which guides them through systematic reasoning steps using targeted, task-specific JSON queries. Our framework features a few-shot example strategy, where each agent receives different few-shots, enhancing ensemble diversity and coverage of the query space. We evaluate our framework on a real-world major bank dataset as well as public benchmark datasets (LCQMC and FiQA), demonstrating significant improvements over single-agent approaches across multiple metrics, including a 14% increase in Top-1 accuracy, an 18% increase in Top-5 accuracy, and a 12% improvement in Mean Reciprocal Rank on our dataset, and similar gains on public benchmarks when compared with traditional and single-agent annotation techniques. Our framework is particularly effective at handling ambiguous queries, making it well-suited for deployment in production banking applications while showing strong generalization capabilities across different domains and languages.

Large Language Models (LLMs) are increasingly deployed as autonomous agents, yet their practical utility is fundamentally constrained by a limited context window and state desynchronization resulting from the LLMs' stateless nature and inefficient context management. These limitations lead to unreliable output, unpredictable behavior, and inefficient resource usage, particularly when interacting with large, structured, and sensitive knowledge systems such as codebases and documents. To address these challenges, we introduce the Gatekeeper Protocol, a novel, domain-agnostic framework that governs agent-system interactions. Our protocol mandates that the agent first operate and reason on a minimalist, low-fidelity "latent state" representation of the system to strategically request high-fidelity context on demand. All interactions are mediated through a unified JSON format that serves as a declarative, state-synchronized protocol, ensuring the agent's model of the system remains verifiably grounded in the system's reality. We demonstrate the efficacy of this protocol with Sage, a reference implementation of the Gatekeeper Protocol for software development. Our results show that this approach significantly increases agent reliability, improves computational efficiency by minimizing token consumption, and enables scalable interaction with complex systems, creating a foundational methodology for building more robust, predictable, and grounded AI agents for any structured knowledge domain.

We present Sadcher, a real-time task assignment framework for heterogeneous multi-robot teams that incorporates dynamic coalition formation and task precedence constraints. Sadcher is trained through Imitation Learning and combines graph attention and transformers to predict assignment rewards between robots and tasks. Based on the predicted rewards, a relaxed bipartite matching step generates high-quality schedules with feasibility guarantees. We explicitly model robot and task positions, task durations, and robots' remaining processing times, enabling advanced temporal and spatial reasoning and generalization to environments with different spatiotemporal distributions compared to training. Trained on optimally solved small-scale instances, our method can scale to larger task sets and team sizes. Sadcher outperforms other learning-based and heuristic baselines on randomized, unseen problems for small and medium-sized teams with computation times suitable for real-time operation. We also explore sampling-based variants and evaluate scalability across robot and task counts. In addition, we release our dataset of 250,000 optimal schedules: https://autonomousrobots.nl/paper_websites/sadcher_MRTA/

Source seeking is an important topic in robotic research, especially considering sound-based sensors since they allow the agents to locate a target even in critical conditions where it is not possible to establish a direct line of sight. In this work, we design a multi- agent switching mode control strategy for acoustic-based target localization. Two scenarios are considered: single source localization, in which the agents are driven maintaining a rigid formation towards the target, and multi-source scenario, in which each agent searches for the targets independently from the others.

Artificial intelligence (AI) is rapidly transforming healthcare, enabling fast development of tools like stress monitors, wellness trackers, and mental health chatbots. However, rapid and low-barrier development can introduce risks of bias, privacy violations, and unequal access, especially when systems ignore real-world contexts and diverse user needs. Many recent methods use AI to detect risks automatically, but this can reduce human engagement in understanding how harms arise and who they affect. We present a human-centered framework that generates user stories and supports multi-agent discussions to help people think creatively about potential benefits and harms before deployment. In a user study, participants who read stories recognized a broader range of harms, distributing their responses more evenly across all 13 harm types. In contrast, those who did not read stories focused primarily on privacy and well-being (58.3%). Our findings show that storytelling helped participants speculate about a broader range of harms and benefits and think more creatively about AI's impact on users.

Planner evaluation in closed-loop simulation often uses rule-based traffic agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely used IDM agents simply follow a lead vehicle and cannot react to vehicles in adjacent lanes, hindering tests of complex interaction capabilities. We address this issue by integrating the state-of-the-art learned traffic agent model SMART into nuPlan. Thus, we are the first to evaluate planners under more realistic conditions and quantify how conclusions shift when narrowing the sim-to-real gap. Our analysis covers 14 recent planners and established baselines and shows that IDM-based simulation overestimates planning performance: nearly all scores deteriorate. In contrast, many planners interact better than previously assumed and even improve in multi-lane, interaction-heavy scenarios like lane changes or turns. Methods trained in closed-loop demonstrate the best and most stable driving performance. However, when reaching their limits in augmented edge-case scenarios, all learned planners degrade abruptly, whereas rule-based planners maintain reasonable basic behavior. Based on our results, we suggest SMART-reactive simulation as a new standard closed-loop benchmark in nuPlan and release the SMART agents as a drop-in alternative to IDM at https://github.com/shgd95/InteractiveClosedLoop.

We introduce NAEL (Non-Anthropocentric Ethical Logic), a novel ethical framework for artificial agents grounded in active inference and symbolic reasoning. Departing from conventional, human-centred approaches to AI ethics, NAEL formalizes ethical behaviour as an emergent property of intelligent systems minimizing global expected free energy in dynamic, multi-agent environments. We propose a neuro-symbolic architecture to allow agents to evaluate the ethical consequences of their actions in uncertain settings. The proposed system addresses the limitations of existing ethical models by allowing agents to develop context-sensitive, adaptive, and relational ethical behaviour without presupposing anthropomorphic moral intuitions. A case study involving ethical resource distribution illustrates NAEL's dynamic balancing of self-preservation, epistemic learning, and collective welfare.

The rapid advancement of multimodal large language models has enabled agents to operate mobile devices by directly interacting with graphical user interfaces, opening new possibilities for mobile automation. However, real-world mobile tasks are often complex and allow for multiple valid solutions. This contradicts current mobile agent evaluation standards: offline static benchmarks can only validate a single predefined "golden path", while online dynamic testing is constrained by the complexity and non-reproducibility of real devices, making both approaches inadequate for comprehensively assessing agent capabilities. To bridge the gap between offline and online evaluation and enhance testing stability, this paper introduces a novel graph-structured benchmarking framework. By modeling the finite states observed during real-device interactions, it achieves static simulation of dynamic behaviors. Building on this, we develop ColorBench, a benchmark focused on complex long-horizon tasks. It supports evaluation of multiple valid solutions, subtask completion rate statistics, and atomic-level capability analysis. ColorBench contains 175 tasks (74 single-app, 101 cross-app) with an average length of over 13 steps. Each task includes at least two correct paths and several typical error paths, enabling quasi-dynamic interaction. By evaluating ColorBench across various baselines, we discover limitations of existing models and propose improvement directions and feasible technical pathways to enhance agents' performance on complex, long-horizon problems based on experimental results. Code and data are available at: https://github.com/MadeAgents/ColorBench.