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.

Developing efficient CUDA kernels is increasingly critical for AI applications such as large-scale LLM training. However, manual kernel design is both costly and time-consuming, motivating automatic approaches that leverage LLMs for code generation. Existing methods for automatic kernel generation, however, often produce low-efficiency kernels, incur high computational overhead, and fail to generalize across settings. In this work, we propose CudaForge, a training-free multi-agent workflow for CUDA kernel generation and optimization. Our workflow is inspired by the iterative workflow of human experts, which contains steps such as developing initial kernels, testing correctness, analyzing hardware feedback, and iterative improvement. More specifically, CudaForge employs two LLM agents: a Coder and a Judge, that iteratively generate, correct, and optimize CUDA kernels, while integrating hardware feedback such as Nsight Compute (NCU) metrics. In extensive evaluations, we show that CudaForge, by leveraging base models like OpenAI-o3, achieves 97.6\% correctness of generated kernels and an average 1.68$\times$ speedup over PyTorch baselines, substantially surpassing state-of-the-art models including OpenAI-o3 and Kevin on KernelBench.Beyond accuracy and speed, CudaForge demonstrates strong generalization across GPUs (A100, RTX 6000, 4090, 3090) and base models (OpenAI-o3, GPT-5, gpt-oss-120B, Claude-Sonnet-4, QwQ-32B), while maintaining high efficiency. In particular, generating an optimized kernel takes about 26.5 minutes on one RTX6000 and incurs about \$ 0.3 API cost, which is significantly cheaper than existing agentic work that costs 6 H100 hours and \$ 5 API cost per kernel. Our results highlight that multi-agent, training-free workflows can enable cost-effective, generalizable, and high-performance CUDA kernel optimization. Code available at https://github.com/OptimAI-Lab/CudaForge

The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a collaborative framework for anomaly and fault diagnostics in robotics. AURA integrates large language models (LLMs), a high-fidelity digital twin (DT), and human-in-the-loop interaction to detect and respond to anomalous behavior in real time. The architecture uses two agents with clear roles: (i) a low-level State Anomaly Characterization Agent that monitors telemetry and converts signals into a structured natural-language problem description, and (ii) a high-level Diagnostic Reasoning Agent that conducts a knowledge-grounded dialogue with an operator to identify root causes, drawing on external sources. Human-validated diagnoses are then converted into new training examples that refine the low-level perceptual model. This feedback loop progressively distills expert knowledge into the AI, transforming it from a static tool into an adaptive partner. We describe the framework's operating principles and provide a concrete implementation, establishing a pattern for trustworthy, continually improving human-robot teams.

Abstract--The rapid expansion of immersive Metaverse applications introduces complex challenges at the intersection of performance, privacy, and environmental sustainability. Centralized architectures fall short in addressing these demands, often resulting in elevated energy consumption, latency, and privacy concerns. This paper proposes MetaF ed, a decentralized federated learning (FL) framework that enables sustainable and intelligent resource orchestration for Metaverse environments. MetaFed integrates (i) multi-agent reinforcement learning for dynamic client selection, (ii) privacy-preserving FL using homomorphic encryption, and (iii) carbon-aware scheduling aligned with renewable energy availability. Evaluations on MNIST and CIF AR-10 using lightweight ResNet architectures demonstrate that MetaFed achieves up to 25% reduction in carbon emissions compared to conventional approaches, while maintaining high accuracy and minimal communication overhead.

The exponential growth of Low Earth Orbit (LEO) satellites has revolutionised Earth Observation (EO) missions, addressing challenges in climate monitoring, disaster management, and more. However, autonomous coordination in multi-satellite systems remains a fundamental challenge. Traditional optimisation approaches struggle to handle the real-time decision-making demands of dynamic EO missions, necessitating the use of Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL). In this paper, we investigate RL-based autonomous EO mission planning by modelling single-satellite operations and extending to multi-satellite constellations using MARL frameworks. We address key challenges, including energy and data storage limitations, uncertainties in satellite observations, and the complexities of decentralised coordination under partial observability. By leveraging a near-realistic satellite simulation environment, we evaluate the training stability and performance of state-of-the-art MARL algorithms, including PPO, IPPO, MAPPO, and HAPPO. Our results demonstrate that MARL can effectively balance imaging and resource management while addressing non-stationarity and reward interdependency in multi-satellite coordination. The insights gained from this study provide a foundation for autonomous satellite operations, offering practical guidelines for improving policy learning in decentralised EO missions.