CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs

The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their growing relevance, there are no benchmarks to assess LLMs' reasoning capability about circuits. Therefore, we created the CIRCUIT dataset consisting of 510 question-answer pairs spanning various levels of analog-circuit-related subjects. The best-performing model on our dataset, GPT-4o, achieves 48.04% accuracy when evaluated on the final numerical answer. To evaluate the robustness of LLMs on our dataset, we introduced a unique feature that enables unit-test-like evaluation by grouping questions into unit tests. In this case, GPT-4o can only pass 27.45% of the unit tests, highlighting that the most advanced LLMs still struggle with understanding circuits, which requires multi-level reasoning, particularly when involving circuit topologies. This circuit-specific benchmark highlights LLMs' limitations, offering valuable insights for advancing their application in analog integrated circuit design.

Systematic Outliers in Large Language Models

Outliers have been widely observed in Large Language Models (LLMs), significantly impacting model performance and posing challenges for model compression. Understanding the functionality and formation mechanisms of these outliers is critically important. Existing works, however, largely focus on reducing the impact of outliers from an algorithmic perspective, lacking an in-depth investigation into their causes and roles. In this work, we provide a detailed analysis of the formation process, underlying causes, and functions of outliers in LLMs. We define and categorize three types of outliers-activation outliers, weight outliers, and attention outliers-and analyze their distributions across different dimensions, uncovering inherent connections between their occurrences and their ultimate influence on the attention mechanism. Based on these observations, we hypothesize and explore the mechanisms by which these outliers arise and function, demonstrating through theoretical derivations and experiments that they emerge due to the self-attention mechanism's softmax operation. These outliers act as implicit context-aware scaling factors within the attention mechanism. As these outliers stem from systematic influences, we term them systematic outliers. Our study not only enhances the understanding of Transformer-based LLMs but also shows that structurally eliminating outliers can accelerate convergence and improve model compression. The code is avilable at https://github.com/an-yongqi/systematic-outliers.

Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments

Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often hindered by the lack of high-quality agent data from the corresponding environments they interact with. We propose Learn-by-interact, a data-centric framework to adapt LLM agents to any given environments without human annotations. Learn-by-interact synthesizes trajectories of agent-environment interactions based on documentations, and constructs instructions by summarizing or abstracting the interaction histories, a process called backward construction. We assess the quality of our synthetic data by using them in both training-based scenarios and training-free in-context learning (ICL), where we craft innovative retrieval approaches optimized for agents. Extensive experiments on SWE-bench, WebArena, OSWorld and Spider2-V spanning across realistic coding, web, and desktop environments show the effectiveness of Learn-by-interact in various downstream agentic tasks -- baseline results are improved by up to 12.2\% for ICL with Claude-3.5 and 19.5\% for training with Codestral-22B. We further demonstrate the critical role of backward construction, which provides up to 14.0\% improvement for training. Our ablation studies demonstrate the efficiency provided by our synthesized data in ICL and the superiority of our retrieval pipeline over alternative approaches like conventional retrieval-augmented generation (RAG). We expect that Learn-by-interact will serve as a foundation for agent data synthesis as LLMs are increasingly deployed at real-world environments.

View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection

View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods' stability under inputs with various view transformations. However, existing research seldom focused on view transformation robustness in multi-view 3D object reconstruction. One direct way to improve the models' VTR is to produce data with more view transformations and add them to model training. Recent progress on large vision models, particularly Stable Diffusion models, has provided great potential for generating 3D models or synthesizing novel view images with only a single image input. Directly deploying these models at inference consumes heavy computation resources and their robustness to view transformations is not guaranteed either. To fully utilize the power of Stable Diffusion models without extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness. Instead of synthesizing random views, we propose a reconstruction error-guided view selection method, which considers the reconstruction errors' spatial distribution of the 3D predictions and chooses the views that could cover the reconstruction errors as much as possible. The methods are trained and tested on sets with large view transformations to validate the 3D reconstruction models' robustness to view transformations. Extensive experiments demonstrate that the proposed method can outperform state-of-the-art 3D reconstruction methods and other view transformation robustness comparison methods.

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Graphical User Interface (GUI) agents hold great potential for automating complex tasks across diverse digital environments, from web applications to desktop software. However, the development of such agents is hindered by the lack of high-quality, multi-step trajectory data required for effective training. Existing approaches rely on expensive and labor-intensive human annotation, making them unsustainable at scale. To address this challenge, we propose AgentTrek, a scalable data synthesis pipeline that generates high-quality GUI agent trajectories by leveraging web tutorials. Our method automatically gathers tutorial-like texts from the internet, transforms them into task goals with step-by-step instructions, and employs a visual-language model agent to simulate their execution in a real digital environment. A VLM-based evaluator ensures the correctness of the generated trajectories. We demonstrate that training GUI agents with these synthesized trajectories significantly improves their grounding and planning performance over the current models. Moreover, our approach is more cost-efficient compared to traditional human annotation methods. This work underscores the potential of guided replay with web tutorials as a viable strategy for large-scale GUI agent training, paving the way for more capable and autonomous digital agents.

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Graphical User Interfaces (GUIs) are critical to human-computer interaction, yet automating GUI tasks remains challenging due to the complexity and variability of visual environments. Existing approaches often rely on textual representations of GUIs, which introduce limitations in generalization, efficiency, and scalability. In this paper, we introduce Aguvis, a unified pure vision-based framework for autonomous GUI agents that operates across various platforms. Our approach leverages image-based observations, and grounding instructions in natural language to visual elements, and employs a consistent action space to ensure cross-platform generalization. To address the limitations of previous work, we integrate explicit planning and reasoning within the model, enhancing its ability to autonomously navigate and interact with complex digital environments. We construct a large-scale dataset of GUI agent trajectories, incorporating multimodal reasoning and grounding, and employ a two-stage training pipeline that first focuses on general GUI grounding, followed by planning and reasoning. Through comprehensive experiments, we demonstrate that Aguvis surpasses previous state-of-the-art methods in both offline and real-world online scenarios, achieving, to our knowledge, the first fully autonomous pure vision GUI agent capable of performing tasks independently without collaboration with external closed-source models. We open-sourced all datasets, models, and training recipes to facilitate future research at https://aguvis-project.github.io/.

IREE Oriented Active RIS-Assisted Green communication System with Outdated CSI

The rapid evolution of communication technologies has spurred a growing demand for energy-efficient network architectures and performance metrics. Active Reconfigurable Intelligent Surfaces (RIS) are emerging as a key component in green network architectures. Compared to passive RIS, active RIS are equipped with amplifiers on each reflecting element, allowing them to simultaneously reflect and amplify signals, thereby overcoming the double multiplicative fading in the phase response, and improving both system coverage and performance. Additionally, the Integrated Relative Energy Efficiency (IREE) metric, as introduced in [1], addresses the dynamic variations in traffic and capacity over time and space, enabling more energy-efficient wireless systems. Building on these advancements, this paper investigates the problem of maximizing IREE in active RIS-assisted green communication systems. However, acquiring perfect Channel State Information (CSI) in practical systems poses significant challenges and costs. To address this, we derive the average achievable rate based on outdated CSI and formulated the corresponding IREE maximization problem, which is solved by jointly optimizing beamforming at both the base station and RIS. Given the non-convex nature of the problem, we propose an Alternating Optimization Successive Approximation (AOSO) algorithm. By applying quadratic transform and relaxation techniques, we simplify the original problem and alternately optimize the beamforming matrices at the base station and RIS. Furthermore, to handle the discrete constraints of the RIS reflection coefficients, we develop a successive approximation method. Experimental results validate our theoretical analysis of the algorithm's convergence , demonstrating the effectiveness of the proposed algorithm and highlighting the superiority of IREE in enhancing the performance of green communication networks.

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce Spider 2.0, an evaluation framework comprising 632 real-world text-to-SQL workflow problems derived from enterprise-level database use cases. The databases in Spider 2.0 are sourced from real data applications, often containing over 1,000 columns and stored in local or cloud database systems such as BigQuery and Snowflake. We show that solving problems in Spider 2.0 frequently requires understanding and searching through database metadata, dialect documentation, and even project-level codebases. This challenge calls for models to interact with complex SQL workflow environments, process extremely long contexts, perform intricate reasoning, and generate multiple SQL queries with diverse operations, often exceeding 100 lines, which goes far beyond traditional text-to-SQL challenges. Our evaluations indicate that based on o1-preview, our code agent framework successfully solves only 17.0% of the tasks, compared with 91.2% on Spider 1.0 and 73.0% on BIRD. Our results on Spider 2.0 show that while language models have demonstrated remarkable performance in code generation -- especially in prior text-to-SQL benchmarks -- they require significant improvement in order to achieve adequate performance for real-world enterprise usage. Progress on Spider 2.0 represents crucial steps towards developing intelligent, autonomous, code agents for real-world enterprise settings. Our code, baseline models, and data are available at https://spider2-sql.github.io.

Attacking Vision-Language Computer Agents via Pop-ups

Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces. Despite such visual inputs becoming more integrated into agentic applications, what types of risks and attacks exist around them still remain unclear. In this work, we demonstrate that VLM agents can be easily attacked by a set of carefully designed adversarial pop-ups, which human users would typically recognize and ignore. This distraction leads agents to click these pop-ups instead of performing the tasks as usual. Integrating these pop-ups into existing agent testing environments like OSWorld and VisualWebArena leads to an attack success rate (the frequency of the agent clicking the pop-ups) of 86% on average and decreases the task success rate by 47%. Basic defense techniques such as asking the agent to ignore pop-ups or including an advertisement notice, are ineffective against the attack.

Can Uncertainty Quantification Enable Better Learning-based Index Tuning?

Index tuning is crucial for optimizing database performance by selecting optimal indexes based on workload. The key to this process lies in an accurate and efficient benefit estimator. Traditional methods relying on what-if tools often suffer from inefficiency and inaccuracy. In contrast, learning-based models provide a promising alternative but face challenges such as instability, lack of interpretability, and complex management. To overcome these limitations, we adopt a novel approach: quantifying the uncertainty in learning-based models' results, thereby combining the strengths of both traditional and learning-based methods for reliable index tuning. We propose Beauty, the first uncertainty-aware framework that enhances learning-based models with uncertainty quantification and uses what-if tools as a complementary mechanism to improve reliability and reduce management complexity. Specifically, we introduce a novel method that combines AutoEncoder and Monte Carlo Dropout to jointly quantify uncertainty, tailored to the characteristics of benefit estimation tasks. In experiments involving sixteen models, our approach outperformed existing uncertainty quantification methods in the majority of cases. We also conducted index tuning tests on six datasets. By applying the Beauty framework, we eliminated worst-case scenarios and more than tripled the occurrence of best-case scenarios.