Four students have died after a school building collapsed in Indonesia on Monday, 99 others were taken to hospital but it is thought 38 people are still trapped. The BBC reports from a nearby centre where relatives face an anxious wait for any updates. Rescuers say they have been able to communicate with seven students and give them oxygen. Watch: Moments as 6.9 magnitude earthquake hit Philippines At least 69 people are killed after it struck on Tuesday night with officials declaring a state of calamity. Social media footage showed the massive crater in Thailand's capital leaving cars teetering on the edge.

Emily Blunt among Hollywood stars outraged over'AI actor' Tilly Norwood An AI actor named Tilly Norwood has been causing a stir after its Dutch creators said the synthetic performer is in talks with talent agencies. Norwood could be mistaken for a young, aspiring actress when one glances at its social media. The brunette poses for photos and showcases a fully AI-generated comedy sketch, where it is described as having girl next door vibes. I may be AI, but I'm feeling very real emotions right now, Tilly's creators wrote on her page. I am so excited for what's coming next!

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action; however, we demonstrate that always planning is computationally expensive and degrades performance on long-horizon tasks, while never planning further limits performance. To address this, we introduce a conceptual framework formalizing dynamic planning for LLM agents, enabling them to flexibly decide when to allocate test-time compute for planning. We propose a simple two-stage training pipeline: (1) supervised fine-tuning on diverse synthetic data to prime models for dynamic planning, and (2) RL to refine this capability in long-horizon environments. Experiments on the Crafter environment show that dynamic planning agents trained with this approach are more sample-efficient and consistently achieve more complex objectives. Additionally, we demonstrate that these agents can be effectively steered by human-written plans, surpassing their independent capabilities. To our knowledge, this work is the first to explore training LLM agents for dynamic test-time compute allocation in sequential decision-making tasks, paving the way for more efficient, adaptive, and controllable agentic systems.

The relationship between computing systems and the brain has served as motivation for pioneering theoreticians since John von Neumann and Alan Turing. Uniform, scale-free biological networks, such as the brain, have powerful properties, including generalizing over time, which is the main barrier for Machine Learning on the path to Universal Reasoning Models. We introduce `Dragon Hatchling' (BDH), a new Large Language Model architecture based on a scale-free biologically inspired network of \$n\$ locally-interacting neuron particles. BDH couples strong theoretical foundations and inherent interpretability without sacrificing Transformer-like performance. BDH is a practical, performant state-of-the-art attention-based state space sequence learning architecture. In addition to being a graph model, BDH admits a GPU-friendly formulation. It exhibits Transformer-like scaling laws: empirically BDH rivals GPT2 performance on language and translation tasks, at the same number of parameters (10M to 1B), for the same training data. BDH can be represented as a brain model. The working memory of BDH during inference entirely relies on synaptic plasticity with Hebbian learning using spiking neurons. We confirm empirically that specific, individual synapses strengthen connection whenever BDH hears or reasons about a specific concept while processing language inputs. The neuron interaction network of BDH is a graph of high modularity with heavy-tailed degree distribution. The BDH model is biologically plausible, explaining one possible mechanism which human neurons could use to achieve speech. BDH is designed for interpretability. Activation vectors of BDH are sparse and positive. We demonstrate monosemanticity in BDH on language tasks. Interpretability of state, which goes beyond interpretability of neurons and model parameters, is an inherent feature of the BDH architecture.

Reinforcement learning in partially observable environments requires agents to act under uncertainty from noisy, incomplete observations. Asymmetric actor-critic methods leverage privileged information during training to improve learning under these conditions. However, existing approaches typically assume full-state access during training. In this work, we challenge this assumption by proposing a novel actor-critic framework, called informed asymmetric actor-critic, that enables conditioning the critic on arbitrary privileged signals without requiring access to the full state. We show that policy gradients remain unbiased under this formulation, extending the theoretical foundation of asymmetric methods to the more general case of privileged partial information. To quantify the impact of such signals, we propose informativeness measures based on kernel methods and return prediction error, providing practical tools for evaluating training-time signals. We validate our approach empirically on benchmark navigation tasks and synthetic partially observable environments, showing that our informed asymmetric method improves learning efficiency and value estimation when informative privileged inputs are available. Our findings challenge the necessity of full-state access and open new directions for designing asymmetric reinforcement learning methods that are both practical and theoretically sound.

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings remain limited, particularly for nonlinear models. In this paper, we investigate the combination of TTT with in-context learning (ICL), where the model is given a few examples from the target distribution at inference time. We analyze this framework in the setting of single-index models $y=σ_*(\langle β, \mathbf{x} \rangle)$, where the feature vector $β$ is drawn from a hidden low-dimensional subspace. For single-layer transformers trained with gradient-based algorithms and adopting TTT, we establish an upper bound on the prediction risk. Our theory reveals that TTT enables the single-layer transformers to adapt to both the feature vector $β$ and the link function $σ_*$, which vary across tasks. This creates a sharp contrast with ICL alone, which is theoretically difficult to adapt to shifts in the link function. Moreover, we provide the convergence rate with respect to the data length, showing the predictive error can be driven arbitrarily close to the noise level as the context size and the network width grow.

Abstract--T o maximize hardware efficiency and performance accuracy in Compute-In-Memory (CIM)-based neural network accelerators for Artificial Intelligence (AI) applications, co-optimizing both software and hardware design parameters is essential. Manual tuning is impractical due to the vast number of parameters and their complex interdependencies. T o effectively automate the design and optimization of CIM-based neural network accelerators, hardware-aware neural architecture search (HW-NAS) techniques can be applied. This work introduces CIMNAS, a joint model-quantization-hardware optimization framework for CIM architectures. CIMNAS simultaneously searches across software parameters, quantization policies, and a broad range of hardware parameters, incorporating device-, circuit-, and architecture-level co-optimizations. CIMNAS experiments were conducted over a search space of 9.9 10 Evaluated on the ImageNet dataset, CIMNAS achieved a reduction in energy-delay-area product (EDAP) ranging from 90.1 to 104.5, an improvement in TOPS/W between 4.68 and 4.82, and an enhancement in TOPS/mm The adaptability and robustness of CIMNAS are demonstrated by extending the framework to support the SRAM-based ResNet50 architecture, achieving up to an 819.5 reduction in EDAP . Unlike other state-of-the-art methods, CIMNAS achieves EDAP-focused optimization without any accuracy loss, generating diverse software-hardware parameter combinations for high-performance CIMbased neural network designs. The exponential growth of Artificial Intelligence (AI) applications and increasing AI model complexity are raising the energy demands for training and processing AI workloads [1]. This trend has created a demand for more sustainable and energy-efficient hardware solutions for AI applications. Compute-In-Memory (CIM) neural network accelerators have emerged as promising architectures for achieving energy-efficient AI processing [2]-[6]. To maximize the hardware efficiency of CIM accelerators and maintain high performance for neural network workloads, it is essential to co-optimize both neural network model parameters and CIM hardware parameters [7]. Mohammed Fouda is with Compumacy for Artificial Intelligence Solutions, Cairo, Egypt.

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks when equipped with external tools. However, current frameworks predominantly rely on sequential processing, leading to inefficient execution particularly for tasks requiring extensive tool interaction. This paper introduces Flash-Searcher, a novel parallel agent reasoning framework that fundamentally reimagines the execution paradigm from sequential chains to directed acyclic graphs (DAGs). Flash-Searcher decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths while maintaining logical constraints. Through dynamic workflow optimization, our framework continuously refines the execution graph based on intermediate results, effectively integrating summary module. Comprehensive evaluations across multiple benchmarks demonstrate that Flash-Searcher consistently outperforms existing approaches. Specifically, it achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks. Furthermore, when distilling this parallel reasoning pipeline into single models, we observe substantial performance gains across diverse backbone architectures, underscoring the generalizability of our methodology. Our work thus represents a significant advance in agent architecture design, offering a more scalable and efficient paradigm for complex reasoning tasks.

Dynamic resource allocation in heterogeneous wireless networks (HetNets) is challenging for traditional methods under varying user loads and channel conditions. We propose a deep reinforcement learning (DRL) framework that jointly optimises transmit power, bandwidth, and scheduling via a multi-objective reward balancing throughput, energy efficiency, and fairness. Using real base station coordinates, we compare Proximal Policy Optimisation (PPO) and Twin Delayed Deep Deterministic Policy Gradient (TD3) against three heuristic algorithms in multiple network scenarios. Our results show that DRL frameworks outperform heuristic algorithms in optimising resource allocation in dynamic networks. These findings highlight key trade-offs in DRL design for future HetNets.

This paper presents a systematic comparative analysis of Variational Quantum Classifier (VQC) configurations for financial fraud detection, encompassing three distinct quantum encoding techniques and comprehensive architectural variations. Through empirical evaluation across multiple entanglement patterns, circuit depths, and optimization strategies,quantum advantages in fraud classification accuracy are demonstrated, achieving up to 94.3 % accuracy with ZZ encoding schemes. The analysis reveals significant performance variations across entanglement topologies, with circular entanglement consistently outperforming linear (90.7) %) and full connectivity (92.0 %) patterns, achieving optimal performance at 93.3 % accuracy. The study introduces novel visualization methodologies for quantum circuit analysis and provides actionable deployment recommendations for practical quantum machine learning implementations. Notably, systematic entanglement pattern analysis shows that circular connectivity provides superior balance between expressivity and trainability while maintaining computational efficiency. These researches offer initial benchmarks for quantum enhanced fraud detection systems and propose potential benefits of quantum machine learning in financial security applications.