Movable Cell-Free Massive MIMO For High-Speed Train Communications: A PPO-Based Antenna Position Optimization

In recent years, high-speed trains (HSTs) communications have developed rapidly to enhance the stability of train operations and improve passenger connectivity experiences. However, as the train continues to accelerate, urgent technological innovations are needed to overcome challenges such as frequency handover and significant Doppler effects. In this paper, we present a novel architecture featuring movable antennas (MAs) to fully exploit macro spatial diversity, enabling a cell-free (CF) massive multiple-input multiple-output (MIMO) system that supports high-speed train communications. Considering the high likelihood of line-of-sight (LoS) transmission in HST scenario, we derive the uplink spectral efficiency (SE) expression for the movable CF massive MIMO system. Moreover, an optimization problem is formulated to maximize the sum SE of the considered system by optimizing the positions of the antennas. Since the formulated problem is non-convex and highly non-linear, we improve a deep reinforcement learning algorithm to address it by using proximal policy optimization (PPO). Different from traditional optimization approaches, which optimize variables separately and alternately, our improved PPO-based approach optimizes all the variables in unison. Simulation results demonstrate that movable CF massive MIMO effectively suppresses the negative impact of the Doppler effect in HST communications.

Channel Estimation for Rydberg Atomic Receivers

The rapid development of the quantum technology presents huge opportunities for 6G communications. Leveraging the quantum properties of highly excited Rydberg atoms, Rydberg atom-based antennas present distinct advantages, such as high sensitivity, broad frequency range, and compact size, over traditional antennas. To realize efficient precoding, accurate channel state information is essential. However, due to the distinct characteristics of atomic receivers, traditional channel estimation algorithms developed for conventional receivers are no longer applicable. To this end, we propose a novel channel estimation algorithm based on projection gradient descent (PGD), which is applicable to both one-dimensional (1D) and twodimensional (2D) arrays. Simulation results are provided to show the effectiveness of our proposed channel estimation method.

Beamforming Design for Beyond Diagonal RIS-Aided Cell-Free Massive MIMO Systems

Reconfigurable intelligent surface (RIS)-aided cell-free (CF) massive multiple-input multiple-output (mMIMO) is a promising architecture for further improving spectral efficiency (SE) with low cost and power consumption. However, conventional RIS has inevitable limitations due to its capability of only reflecting signals. In contrast, beyond-diagonal RIS (BD-RIS), with its ability to both reflect and transmit signals, has gained great attention. This correspondence focuses on using BD-RIS to improve the sum SE of CF mMIMO systems. This requires completing the beamforming design under the transmit power constraints and unitary constraints of the BD-RIS, by optimizing active and passive beamformer simultaneously. To tackle this issue, we introduce an alternating optimization algorithm that decomposes it using fractional programming and solves the subproblems alternatively. Moreover, to address the challenge introduced by the unitary constraint on the beamforming matrix of the BD-RIS, a manifold optimization algorithm is proposed to solve the problem optimally. Simulation results show that BD-RISs outperform RISs comprehensively, especially in the case of the full connected architecture which achieves the best performance, enhancing the sum SE by around 40% compared to ideal RISs.

MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

Large Language Models (LLMs) have shown impressive performance on existing medical question-answering benchmarks. This high performance makes it increasingly difficult to meaningfully evaluate and differentiate advanced methods. We present MedAgentsBench, a benchmark that focuses on challenging medical questions requiring multi-step clinical reasoning, diagnosis formulation, and treatment planning-scenarios where current models still struggle despite their strong performance on standard tests. Drawing from seven established medical datasets, our benchmark addresses three key limitations in existing evaluations: (1) the prevalence of straightforward questions where even base models achieve high performance, (2) inconsistent sampling and evaluation protocols across studies, and (3) lack of systematic analysis of the interplay between performance, cost, and inference time. Through experiments with various base models and reasoning methods, we demonstrate that the latest thinking models, DeepSeek R1 and OpenAI o3, exhibit exceptional performance in complex medical reasoning tasks. Additionally, advanced search-based agent methods offer promising performance-to-cost ratios compared to traditional approaches. Our analysis reveals substantial performance gaps between model families on complex questions and identifies optimal model selections for different computational constraints. Our benchmark and evaluation framework are publicly available at https://github.com/gersteinlab/medagents-benchmark.

TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization

Urban traffic optimization is critical for improving transportation efficiency and alleviating congestion, particularly in large-scale dynamic networks. Traditional methods, such as Dijkstra's and Floyd's algorithms, provide effective solutions in static settings, but they struggle with the spatial-temporal complexity of real-world traffic flows. In this work, we propose TrafficKAN-GCN, a hybrid deep learning framework combining Kolmogorov-Arnold Networks (KAN) with Graph Convolutional Networks (GCN), designed to enhance urban traffic flow optimization. By integrating KAN's adaptive nonlinear function approximation with GCN's spatial graph learning capabilities, TrafficKAN-GCN captures both complex traffic patterns and topological dependencies. We evaluate the proposed framework using real-world traffic data from the Baltimore Metropolitan area. Compared with baseline models such as MLP-GCN, standard GCN, and Transformer-based approaches, TrafficKAN-GCN achieves competitive prediction accuracy while demonstrating improved robustness in handling noisy and irregular traffic data. Our experiments further highlight the framework's ability to redistribute traffic flow, mitigate congestion, and adapt to disruptive events, such as the Francis Scott Key Bridge collapse. This study contributes to the growing body of work on hybrid graph learning for intelligent transportation systems, highlighting the potential of combining KAN and GCN for real-time traffic optimization. Future work will focus on reducing computational overhead and integrating Transformer-based temporal modeling for enhanced long-term traffic prediction. The proposed TrafficKAN-GCN framework offers a promising direction for data-driven urban mobility management, balancing predictive accuracy, robustness, and computational efficiency.

Joint Power Allocation and Phase Shift Design for Stacked Intelligent Metasurfaces-aided Cell-Free Massive MIMO Systems with MARL

Cell-free (CF) massive multiple-input multiple-output (mMIMO) systems offer high spectral efficiency (SE) through multiple distributed access points (APs). However, the large number of antennas increases power consumption. We propose incorporating stacked intelligent metasurfaces (SIM) into CF mMIMO systems as a cost-effective, energy-efficient solution. This paper focuses on optimizing the joint power allocation of APs and the phase shift of SIMs to maximize the sum SE. To address this complex problem, we introduce a fully distributed multi-agent reinforcement learning (MARL) algorithm. Our novel algorithm, the noisy value method with a recurrent policy in multi-agent policy optimization (NVR-MAPPO), enhances performance by encouraging diverse exploration under centralized training and decentralized execution. Simulations demonstrate that NVR-MAPPO significantly improves sum SE and robustness across various scenarios.

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM.

Atom of Thoughts for Markov LLM Test-Time Scaling

Large Language Models (LLMs) achieve superior performance through training-time scaling, and test-time scaling further enhances their capabilities by conducting effective reasoning during inference. However, as the scale of reasoning increases, existing test-time scaling methods suffer from accumulated historical information, which not only wastes computational resources but also interferes with effective reasoning. To address this issue, we observe that complex reasoning progress is often achieved by solving a sequence of independent subquestions, each being self-contained and verifiable. These subquestions are essentially atomic questions, relying primarily on their current state rather than accumulated history, similar to the memoryless transitions in a Markov process. Based on this observation, we propose Atom of Thoughts (AoT), where each state transition in the reasoning process consists of decomposing the current question into a dependency-based directed acyclic graph and contracting its subquestions, forming a new atomic question state. This iterative decomposition-contraction process continues until reaching directly solvable atomic questions, naturally realizing Markov transitions between question states. Furthermore, these atomic questions can be seamlessly integrated into existing test-time scaling methods, enabling AoT to serve as a plug-in enhancement for improving reasoning capabilities. Experiments across six benchmarks demonstrate the effectiveness of AoT both as a standalone framework and a plug-in enhancement. Notably, on HotpotQA, when applied to gpt-4o-mini, AoT achieves an 80.6% F1 score, surpassing o3-mini by 3.4% and DeepSeek-R1 by 10.6%. The code will be available at https://github.com/qixucen/atom.

Self-Supervised Prompt Optimization

Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and iterative experimentation. While existing prompt optimization methods aim to automate this process, they rely heavily on external references such as ground truth or by humans, limiting their applicability in real-world scenarios where such data is unavailable or costly to obtain. To address this, we propose Self-Supervised Prompt Optimization (SPO), a cost-efficient framework that discovers effective prompts for both closed and open-ended tasks without requiring external reference. Motivated by the observations that prompt quality manifests directly in LLM outputs and LLMs can effectively assess adherence to task requirements, we derive evaluation and optimization signals purely from output comparisons. Specifically, SPO selects superior prompts through pairwise output comparisons evaluated by an LLM evaluator, followed by an LLM optimizer that aligns outputs with task requirements. Extensive experiments demonstrate that SPO outperforms state-of-the-art prompt optimization methods, achieving comparable or superior results with significantly lower costs (e.g., 1.1% to 5.6% of existing methods) and fewer samples (e.g., three samples). The code is available at https://github.com/geekan/MetaGPT.

Examining the Robustness of Large Language Models across Language Complexity

With the advancement of large language models (LLMs), an increasing number of student models have leveraged LLMs to analyze textual artifacts generated by students to understand and evaluate their learning. These student models typically employ pre-trained LLMs to vectorize text inputs into embeddings and then use the embeddings to train models to detect the presence or absence of a construct of interest. However, how reliable and robust are these models at processing language with different levels of complexity? In the context of learning where students may have different language backgrounds with various levels of writing skills, it is critical to examine the robustness of such models to ensure that these models work equally well for text with varying levels of language complexity. Coincidentally, a few (but limited) research studies show that the use of language can indeed impact the performance of LLMs. As such, in the current study, we examined the robustness of several LLM-based student models that detect student self-regulated learning (SRL) in math problem-solving. Specifically, we compared how the performance of these models vary using texts with high and low lexical, syntactic, and semantic complexity measured by three linguistic measures.