TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents

Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-purpose capabilities for adapting to diverse scenarios and tasks. Real-time strategy (RTS) games serve as an ideal testbed for evaluating these two capabilities, as their inherent gameplay requires both macro-level strategic planning and micro-level tactical adaptation and action execution. Existing RTS game-based environments either suffer from relatively high computational demands or lack support for textual observations, which has constrained the use of RTS games for LLM evaluation. Motivated by this, we present TowerMind, a novel environment grounded in the tower defense (TD) subgenre of RTS games. TowerMind preserves the key evaluation strengths of RTS games for assessing LLMs, while featuring low computational demands and a multimodal observation space, including pixel-based, textual, and structured game-state representations. In addition, TowerMind supports the evaluation of model hallucination and provides a high degree of customizability. We design five benchmark levels to evaluate several widely used LLMs under different multimodal input settings. The results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions. The experiments further highlight key limitations in LLM behavior, such as inadequate planning validation, a lack of multifinality in decision-making, and inefficient action use. We also evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight and multimodal design, TowerMind complements the existing RTS game-based environment landscape and introduces a new benchmark for the AI agent field. The source code is publicly available on GitHub(https://github.com/tb6147877/TowerMind).

Intelligent recognition of GPR road hidden defect images based on feature fusion and attention mechanism

Ground Penetrating Radar (GPR) has emerged as a pivotal tool for non-destructive evaluation of subsurface road defects. However, conventional GPR image interpretation remains heavily reliant on subjective expertise, introducing inefficiencies and inaccuracies. This study introduces a comprehensive framework to address these limitations: (1) A DCGAN-based data augmentation strategy synthesizes high-fidelity GPR images to mitigate data scarcity while preserving defect morphology under complex backgrounds; (2) A novel Multi-modal Chain and Global Attention Network (MCGA-Net) is proposed, integrating Multi-modal Chain Feature Fusion (MCFF) for hierarchical multi-scale defect representation and Global Attention Mechanism (GAM) for context-aware feature enhancement; (3) MS COCO transfer learning fine-tunes the backbone network, accelerating convergence and improving generalization. Ablation and comparison experiments validate the framework's efficacy. MCGA-Net achieves Precision (92.8%), Recall (92.5%), and mAP@50 (95.9%). In the detection of Gaussian noise, weak signals and small targets, MCGA-Net maintains robustness and outperforms other models. This work establishes a new paradigm for automated GPR-based defect detection, balancing computational efficiency with high accuracy in complex subsurface environments.

Lightweight framework for underground pipeline recognition and spatial localization based on multi-view 2D GPR images

To address the issues of weak correlation between multi-view features, low recognition accuracy of small-scale targets, and insufficient robustness in complex scenarios in underground pipeline detection using 3D GPR, this paper proposes a 3D pipeline intelligent detection framework. First, based on a B/C/D-Scan three-view joint analysis strategy, a three-dimensional pipeline three-view feature evaluation method is established by cross-validating forward simulation results obtained using FDTD methods with actual measurement data. Second, the DCO-YOLO framework is proposed, which integrates DySample, CGLU, and OutlookAttention cross-dimensional correlation mechanisms into the original YOLOv11 algorithm, significantly improving the small-scale pipeline edge feature extraction capability. Furthermore, a 3D-DIoU spatial feature matching algorithm is proposed, which integrates three-dimensional geometric constraints and center distance penalty terms to achieve automated association of multi-view annotations. The three-view fusion strategy resolves inherent ambiguities in single-view detection. Experiments based on real urban underground pipeline data show that the proposed method achieves accuracy, recall, and mean average precision of 96.2%, 93.3%, and 96.7%, respectively, in complex multi-pipeline scenarios, which are 2.0%, 2.1%, and 0.9% higher than the baseline model. Ablation experiments validated the synergistic optimization effect of the dynamic feature enhancement module and Grad-CAM++ heatmap visualization demonstrated that the improved model significantly enhanced its ability to focus on pipeline geometric features. This study integrates deep learning optimization strategies with the physical characteristics of 3D GPR, offering an efficient and reliable novel technical framework for the intelligent recognition and localization of underground pipelines.

DMA: Online RAG Alignment with Human Feedback

Retrieval-augmented generation (RAG) systems often rely on static retrieval, limiting adaptation to evolving intent and content drift. We introduce Dynamic Memory Alignment (DMA), an online learning framework that systematically incorporates multi-granularity human feedback to align ranking in interactive settings. DMA organizes document-, list-, and response-level signals into a coherent learning pipeline: supervised training for pointwise and listwise rankers, policy optimization driven by response-level preferences, and knowledge distillation into a lightweight scorer for low-latency serving. Throughout this paper, memory refers to the model's working memory, which is the entire context visible to the LLM for In-Context Learning. We adopt a dual-track evaluation protocol mirroring deployment: (i) large-scale online A/B ablations to isolate the utility of each feedback source, and (ii) few-shot offline tests on knowledge-intensive benchmarks. Online, a multi-month industrial deployment further shows substantial improvements in human engagement. Offline, DMA preserves competitive foundational retrieval while yielding notable gains on conversational QA (TriviaQA, HotpotQA). Taken together, these results position DMA as a principled approach to feedback-driven, real-time adaptation in RAG without sacrificing baseline capability.

Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark

This paper presents a mixed traffic control policy designed to optimize traffic efficiency across diverse road topologies, addressing issues of congestion prevalent in urban environments. A model-free reinforcement learning (RL) approach is developed to manage large-scale traffic flow, using data collected by autonomous vehicles to influence human-driven vehicles. A real-world mixed traffic control benchmark is also released, which includes 444 scenarios from 20 countries, representing a wide geographic distribution and covering a variety of scenarios and road topologies. This benchmark serves as a foundation for future research, providing a realistic simulation environment for the development of effective policies. Comprehensive experiments demonstrate the effectiveness and adaptability of the proposed method, achieving better performance than existing traffic control methods in both intersection and roundabout scenarios. To the best of our knowledge, this is the first project to introduce a real-world complex scenarios mixed traffic control benchmark. Videos and code of our work are available at https://sites.google.com/berkeley.edu/mixedtrafficplus/home

Learning to Change: Choreographing Mixed Traffic Through Lateral Control and Hierarchical Reinforcement Learning

The management of mixed traffic that consists of robot vehicles (RVs) and human-driven vehicles (HVs) at complex intersections presents a multifaceted challenge. Traditional signal controls often struggle to adapt to dynamic traffic conditions and heterogeneous vehicle types. Recent advancements have turned to strategies based on reinforcement learning (RL), leveraging its model-free nature, real-time operation, and generalizability over different scenarios. We introduce a hierarchical RL framework to manage mixed traffic through precise longitudinal and lateral control of RVs. Our proposed hierarchical framework combines the state-of-the-art mixed traffic control algorithm as a high level decision maker to improve the performance and robustness of the whole system. Our experiments demonstrate that the framework can reduce the average waiting time by up to 54% compared to the state-of-the-art mixed traffic control method. When the RV penetration rate exceeds 60%, our technique consistently outperforms conventional traffic signal control programs in terms of the average waiting time for all vehicles at the intersection.

GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping

Constructing a 3D scene capable of accommodating open-ended language queries, is a pivotal pursuit, particularly within the domain of robotics. Such technology facilitates robots in executing object manipulations based on human language directives. To tackle this challenge, some research efforts have been dedicated to the development of language-embedded implicit fields. However, implicit fields (e.g. NeRF) encounter limitations due to the necessity of processing a large number of input views for reconstruction, coupled with their inherent inefficiencies in inference. Thus, we present the GaussianGrasper, which utilizes 3D Gaussian Splatting to explicitly represent the scene as a collection of Gaussian primitives. Our approach takes a limited set of RGB-D views and employs a tile-based splatting technique to create a feature field. In particular, we propose an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently and accurately distill language embeddings derived from foundational models. With the reconstructed geometry of the Gaussian field, our method enables the pre-trained grasping model to generate collision-free grasp pose candidates. Furthermore, we propose a normal-guided grasp module to select the best grasp pose. Through comprehensive real-world experiments, we demonstrate that GaussianGrasper enables robots to accurately query and grasp objects with language instructions, providing a new solution for language-guided manipulation tasks. Data and codes can be available at https://github.com/MrSecant/GaussianGrasper.

Analyzing Emissions and Energy Efficiency in Mixed Traffic Control at Unsignalized Intersections

Greenhouse gas emissions have dramatically risen since the early 1900s with U.S. transportation generating 28% of the U.S' emissions. As such, there is interest in reducing transportation-related emissions. Specifically, sustainability research has sprouted around signalized intersections as intersections allow different streams of traffic to cross and change directions. Recent research has developed mixed traffic control eco-driving strategies at signalized intersections to decrease emissions. However, the inherent structure of a signalized intersection generates increased emissions by creating frequent acceleration/deceleration events, excessive idling from traffic congestion, and stop-and-go waves. Thus, we believe unsignalized intersections hold potential for further sustainability improvements. In this work, we provide an emissions analysis on unsignalized intersections with complex, real-world topologies and traffic demands where mixed traffic control strategies are employed by robot vehicles (RVs) to reduce waiting times and congestion. We find with at least 10% RV penetration rate, RVs generate less fuel consumption and NOx emissions than signalized intersections by up to 27% and 28%, respectively. With at least 30% RVs, CO and HC emissions are reduced by up to 42% and 43%, respectively. Additionally, RVs can reduce emissions across the whole network despite only employing their strategies at the intersections.

Large-scale Mixed Traffic Control Using Dynamic Vehicle Routing and Privacy-Preserving Crowdsourcing

Controlling and coordinating urban traffic flow through robot vehicles is emerging as a novel transportation paradigm for the future. While this approach garners growing attention from researchers and practitioners, effectively managing and coordinating large-scale mixed traffic remains a challenge. We introduce an effective framework for large-scale mixed traffic control via privacy-preserving crowdsourcing and dynamic vehicle routing. Our framework consists of three modules: a privacy-protecting crowdsensing method, a graph propagation-based traffic forecasting method, and a privacy-preserving route selection mechanism. We evaluate our framework using a real-world road network. The results show that our framework accurately forecasts traffic flow, efficiently mitigates network-wide RV shortage issue, and coordinates large-scale mixed traffic. Compared to other baseline methods, our framework not only reduces the RV shortage issue up to 69.4% but also reduces the average waiting time of all vehicles in the network up to 27%.

Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training

Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design (CAD) models and languages. The main challenges are the domain gaps between the CAD models and the real scene's objects, including model-to-scene (from a single model to the scene) and synthetic-to-real (from synthetic model to real scene's object). To handle the above challenges, Model2Scene first simulates a crowded scene by mixing data-augmented CAD models. Next, we propose a novel feature regularization operation, termed Deep Convex-hull Regularization (DCR), to project point features into a unified convex hull space, reducing the domain gap. Ultimately, we impose contrastive loss on language embedding and the point features of CAD models to pre-train the 3D network. Extensive experiments verify the learned 3D scene representation is beneficial for various downstream tasks, including label-free 3D object salient detection, label-efficient 3D scene perception and zero-shot 3D semantic segmentation. Notably, Model2Scene yields impressive label-free 3D object salient detection with an average mAP of 46.08\% and 55.49\% on the ScanNet and S3DIS datasets, respectively. The code will be publicly available.