Large language models (LLMs) have recently transformed from text-based assistants to autonomous agents capable of planning, reasoning, and iteratively improving their actions. While numerical reward signals and verifiers can effectively rank candidate actions, they often provide limited contextual guidance. In contrast, natural language feedback better aligns with the generative capabilities of LLMs, providing richer and more actionable suggestions. However, parsing and implementing this feedback effectively can be challenging for LLM-based agents. In this work, we introduce Critique-Guided Improvement (CGI), a novel two-player framework, comprising an actor model that explores an environment and a critic model that generates detailed nature language feedback. By training the critic to produce fine-grained assessments and actionable revisions, and the actor to utilize these critiques, our approach promotes more robust exploration of alternative strategies while avoiding local optima. Experiments in three interactive environments show that CGI outperforms existing baselines by a substantial margin. Notably, even a small critic model surpasses GPT-4 in feedback quality. The resulting actor achieves state-of-the-art performance, demonstrating the power of explicit iterative guidance to enhance decision-making in LLM-based agents.

Language models (LMs) are machine learning models designed to predict linguistic patterns by estimating the probability of word sequences based on large-scale datasets, such as text. LMs have a wide range of applications in natural language processing (NLP) tasks, including autocomplete and machine translation. Although larger datasets typically enhance LM performance, scalability remains a challenge due to constraints in computational power and resources. Distributed computing strategies offer essential solutions for improving scalability and managing the growing computational demand. Further, the use of sensitive datasets in training and deployment raises significant privacy concerns. Recent research has focused on developing decentralized techniques to enable distributed training and inference while utilizing diverse computational resources and enabling edge AI. This paper presents a survey on distributed solutions for various LMs, including large language models (LLMs), vision language models (VLMs), multimodal LLMs (MLLMs), and small language models (SLMs). While LLMs focus on processing and generating text, MLLMs are designed to handle multiple modalities of data (e.g., text, images, and audio) and to integrate them for broader applications. To this end, this paper reviews key advancements across the MLLM pipeline, including distributed training, inference, fine-tuning, and deployment, while also identifying the contributions, limitations, and future areas of improvement. Further, it categorizes the literature based on six primary focus areas of decentralization. Our analysis describes gaps in current methodologies for enabling distributed solutions for LMs and outline future research directions, emphasizing the need for novel solutions to enhance the robustness and applicability of distributed LMs.

We consider price competition among multiple sellers over a selling horizon of $T$ periods. In each period, sellers simultaneously offer their prices and subsequently observe their respective demand that is unobservable to competitors. The demand function for each seller depends on all sellers' prices through a private, unknown, and nonlinear relationship. To address this challenge, we propose a semi-parametric least-squares estimation of the nonlinear mean function, which does not require sellers to communicate demand information. We show that when all sellers employ our policy, their prices converge at a rate of $O(T^{-1/7})$ to the Nash equilibrium prices that sellers would reach if they were fully informed. Each seller incurs a regret of $O(T^{5/7})$ relative to a dynamic benchmark policy. A theoretical contribution of our work is proving the existence of equilibrium under shape-constrained demand functions via the concept of $s$-concavity and establishing regret bounds of our proposed policy. Technically, we also establish new concentration results for the least squares estimator under shape constraints. Our findings offer significant insights into dynamic competition-aware pricing and contribute to the broader study of non-parametric learning in strategic decision-making.

Information and free-energy maximization are physics principles that provide general rules for an agent to optimize actions in line with specific goals and policies. These principles are the building blocks for designing decision-making policies capable of efficient performance with only partial information. Notably, the information maximization principle has shown remarkable success in the classical bandit problem and has recently been shown to yield optimal algorithms for Gaussian and sub-Gaussian reward distributions. This article explores a broad extension of physics-based approaches to more complex and structured bandit problems. To this end, we cover three distinct types of bandit problems, where information maximization is adapted and leads to strong performance. Since the main challenge of information maximization lies in avoiding over-exploration, we highlight how information is tailored at various levels to mitigate this issue, paving the way for more efficient and robust decision-making strategies.

There is a realistic chance that one of the UK's largest oil refineries can be converted into a hub for green chemicals, sustainable fuels and plastics, Scotland's first minister says. Grangemouth oil refinery, which is being shut down by its UK and Chinese owners PetroIneos this year with the loss of 400 jobs, could become a world leader in low carbon chemicals and green fuels, John Swinney told media on Wednesday. The refinery's closure, after 100 years of production, is expected to hit up to 2,000 jobs in the east of Scotland. Trade union leaders and policymakers see Grangemouth as a casestudy in ensuring the transition from oil and gas is fair and just. Swinney said workers and local businesses faced "enormous difficulties".

President Trump this week continued to make his environmental priorities clear by vowing to open up hundreds of coal power plants in the United States in an effort to advance competition against China. "After years of being held captive by Environmental Extremists, Lunatics, Radicals, and Thugs, allowing other Countries, in particular China, to gain tremendous Economic advantage over us by opening up hundreds of all Coal Fire Power Plants, I am authorizing my Administration to immediately begin producing Energy with BEAUTIFUL, CLEAN COAL," Trump wrote in a post on social media Monday. Though the post was not linked to any particular policy plans or documents, it arrives as the White House takes aim at various environmental agencies and clean-energy initiatives. In the last week alone, the administration has announced plans to significantly roll back regulations that govern coal production and to potentially lay off up to 65% of scientists and researchers at the Environmental Protection Agency, among other actions. Coal accounts for about 16% of the country's electricity generation, according to the U.S. Energy Information Administration -- down from about 50% in 2000 as natural gas and nuclear and renewable energy have grown.

Materials synthesis is vital for innovations such as energy storage, catalysis, electronics, and biomedical devices. Yet, the process relies heavily on empirical, trial-and-error methods guided by expert intuition. Our work aims to support the materials science community by providing a practical, data-driven resource. We have curated a comprehensive dataset of 17K expert-verified synthesis recipes from open-access literature, which forms the basis of our newly developed benchmark, AlchemyBench. AlchemyBench offers an end-to-end framework that supports research in large language models applied to synthesis prediction. It encompasses key tasks, including raw materials and equipment prediction, synthesis procedure generation, and characterization outcome forecasting. We propose an LLM-as-a-Judge framework that leverages large language models for automated evaluation, demonstrating strong statistical agreement with expert assessments. Overall, our contributions offer a supportive foundation for exploring the capabilities of LLMs in predicting and guiding materials synthesis, ultimately paving the way for more efficient experimental design and accelerated innovation in materials science.

The impressive capabilities of Large Language Models (LLMs) across diverse tasks are now well-established, yet their effective deployment necessitates careful hyperparameter optimization. Through extensive empirical studies involving grid searches across diverse configurations, we discover universal scaling laws governing these hyperparameters: optimal learning rate follows a power-law relationship with both model parameters and data sizes, while optimal batch size scales primarily with data sizes. Our analysis reveals a convex optimization landscape for hyperparameters under fixed models and data size conditions. This convexity implies an optimal hyperparameter plateau. We contribute a universal, plug-and-play optimal hyperparameter tool for the community. Its estimated values on the test set are merely 0.09% away from the globally optimal LLM performance found via an exhaustive search. These laws demonstrate remarkable robustness across variations in model sparsity, training data distribution, and model shape. To our best known, this is the first work that unifies different model shapes and structures, such as Mixture-of-Experts models and dense transformers, as well as establishes optimal hyperparameter scaling laws across diverse data distributions. This exhaustive optimization process demands substantial computational resources, utilizing nearly one million NVIDIA H800 GPU hours to train 3,700 LLMs of varying sizes and hyperparameters from scratch and consuming approximately 100 trillion tokens in total. To facilitate reproducibility and further research, we will progressively release all loss measurements and model checkpoints through our designated repository https://step-law.github.io/

In motion simulation, motion cueing algorithms are used for the trajectory planning of the motion simulator platform, where workspace limitations prevent direct reproduction of reference trajectories. Strategies such as motion washout, which return the platform to its center, are crucial in these settings. For serial robotic MSPs with highly nonlinear workspaces, it is essential to maximize the efficient utilization of the MSPs kinematic and dynamic capabilities. Traditional approaches, including classical washout filtering and linear model predictive control, fail to consider platform-specific, nonlinear properties, while nonlinear model predictive control, though comprehensive, imposes high computational demands that hinder real-time, pilot-in-the-loop application without further simplification. To overcome these limitations, we introduce a novel approach using deep reinforcement learning for motion cueing, demonstrated here for the first time in a 6-degree-of-freedom setting with full consideration of the MSPs kinematic nonlinearities. Previous work by the authors successfully demonstrated the application of DRL to a simplified 2-DOF setup, which did not consider kinematic or dynamic constraints. This approach has been extended to all 6 DOF by incorporating a complete kinematic model of the MSP into the algorithm, a crucial step for enabling its application on a real motion simulator. The training of the DRL-MCA is based on Proximal Policy Optimization in an actor-critic implementation combined with an automated hyperparameter optimization. After detailing the necessary training framework and the algorithm itself, we provide a comprehensive validation, demonstrating that the DRL MCA achieves competitive performance against established algorithms. Moreover, it generates feasible trajectories by respecting all system constraints and meets all real-time requirements with low...

Numerical simulations of seismic wave propagation are crucial for investigating velocity structures and improving seismic hazard assessment. However, standard methods such as finite difference or finite element are computationally expensive. Recent studies have shown that a new class of machine learning models, called neural operators, can solve the elastodynamic wave equation orders of magnitude faster than conventional methods. Full waveform inversion is a prime beneficiary of the accelerated simulations. Neural operators, as end-to-end differentiable operators, combined with automatic differentiation, provide an alternative approach to the adjoint-state method. Since neural operators do not involve the Born approximation, when used for full waveform inversion they have the potential to include additional phases and alleviate cycle-skipping problems present in traditional adjoint-state formulations. In this study, we demonstrate the application of neural operators for full waveform inversion on a real seismic dataset, which consists of several nodal transects collected across the San Gabriel, Chino, and San Bernardino basins in the Los Angeles metropolitan area.