Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31. 1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design.

Large language models (LLMs) augmented with knowledge graphs (KGs) have exhibited great potential for complex reasoning tasks. However, existing approaches often struggle with incomplete subgraph retrieval and inaccurate semantic alignment, which hinder reasoning performance and answer quality. In this paper, we present Faico, a KG-enhanced reasoning framework designed to achieve both semantic faithfulness and structural completeness. Faico decouples model inference from graph traversal by integrating a fine-tuned LLM-based relation type generator for accurate semantic mapping and a KG retriever for reasoning subgraph search. Based on the predicted relation types, we model the reasoning subgraph (RS) as a k-bounded edge type (k-BET) subgraph, where k constrains the recurrence of relation types within paths, and devise a budget-dominance-based algorithm to efficiently identify the maximal k-BET subgraph. Our framework ensures comprehensive coverage of relevant multi-hop relations while reducing computational overhead. Through extensive experiments on multiple KGQA benchmarks, Faico demonstrates improvements in both effectiveness and efficiency over LLM-native and state-of-the-art KG-augmented reasoning baselines, delivering more accurate, complete answers and lower inference latency.

Pairwise preferences over model responses are widely collected to evaluate and provide feedback to large language models (LLMs).Given two alternative model responses to the same input, a human or AI annotator selects the "better" response.This approach can provide feedback for domains where other hard-coded metrics are difficult to obtain (e.g., chat response quality), thereby helping model evaluation or training.However, for some domains high-quality pairwise comparisons can be tricky to obtain -from AI and humans.For example, for responses with many factual statements, annotators may disproportionately weigh writing quality rather than underlying facts.In this work, we explore augmenting standard AI annotator systems with additional tools to improve performance on three challenging response domains: long-form factual, math and code tasks.We propose a tool-using agentic system to provide higher quality feedback on these domains.Our system uses web-search and code execution to ground itself based on external validation, independent of the LLM's internal knowledge and biases.We provide extensive experimental results evaluating our method across the three targeted response domains as well as general annotation tasks, using RewardBench (incl.Al-pacaEval and LLMBar), RewardMath, as well as three new datasets for domains with saturated pre-existing datasets.Our results indicate that external tools can indeed improve AI annotator performance in many, but not all, cases.More generally, our experiments highlight the sensitivity of AI annotator performance to simple parameters (e.g., prompt) and the need for improved (non-saturated) annotator benchmarks.We share our code at github.com/apple/ml-agent-evaluator.

Intel SGX is susceptible to intra-enclave software vulnerabilities. Existing automated bug-finding methods primarily focus on fuzzing enclave boundaries for SGX applications in simulated, rather than actual hardware-protected enclaves. This limits the ability to identify potential security violations originating from within SGX application code. This paper presents IntraFuzz, the first system that enables efficient fuzzing of SGX applications inside actual hardware enclaves. We evaluated IntraFUZZ with 21 real-world SGX applications, running on Intel Xeon scalable processors with up to 256 GB of enclave page cache. IntraFuzz successfully detected all vulnerabilities in SGX application code previously identified by the state-of-the-art tool EnclaveFuzz, as well as 6 previously undiscovered vulnerabilities. These results highlight the importance of hardware-based fuzzing in securing SGX applications.

The generalization capabilities of vision-language-action (VLA) models to unseen tasks are crucial to achieving general-purpose robotic manipulation in open-world settings. However, the cross-task generalization capabilities of existing VLA models remain significantly underexplored. To address this gap, we introduce **AGNOSTOS**, a novel simulation benchmark designed to rigorously evaluate cross-task zero-shot generalization in manipulation. AGNOSTOS comprises 23 unseen manipulation tasks for test—distinct from common training task distributions—and incorporates two levels of generalization difficulty to assess robustness. Our systematic evaluation reveals that current VLA models, despite being trained on diverse datasets, struggle to generalize effectively to these unseen tasks. To overcome this limitation, we propose **Cross-Task In-Context Manipulation (X-ICM)**, a method that conditions large language models (LLMs) on in-context demonstrations from seen tasks to predict action sequences for unseen tasks. Additionally, we introduce a **dynamics-guided sample selection** strategy that identifies relevant demonstrations by capturing cross-task dynamics. On AGNOSTOS, X-ICM significantly improves cross-task zero-shot generalization performance over leading VLAs, achieving improvements of 6.0\% over $\pi_0$ and 7.9\% over VoxPoser. We believe AGNOSTOS and X-ICM will serve as valuable tools for advancing general-purpose robotic manipulation.

Traffic encryption is widely used to protect communication privacy but is increasingly exploited by attackers to conceal malicious activities. Existing malicious encrypted traffic detection methods rely on large amounts of labeled samples for training, limiting their ability to quickly respond to new attacks. These methods also are vulnerable to traffic obfuscation strategies, such as injecting dummy packets. In this paper, we proposeSmartDetector, a robust malicious encrypted traffic detection method via contrastive learning. We first propose a novel traffic representation named Semantic Attribute Matrix (SAM), which can effectively distinguish between malicious and benign traffic. We also design a data augmentation method to generate diverse traffic samples, which makes the detection model more robust against different traffic obfuscation strategies. We propose a malicious encrypted traffic classifier that first pre-trains a model via contrastive learning to learn deep representations from unlabeled data, then fine-tunes the model with a supervised classifier to achieve accurate detection even with only a few labeled samples. We conduct extensive experiments with five public datasets to evaluate the performance of SmartDetector. The results demonstrate that it outperforms the state-of-the-art (SOTA) methods in three typical scenarios. Specifically, in the evasion attack detection scenario, SmartDetector achieves an F1 score and AUC above 93%, with average improvements of 19.84% and 18.17% over the SOTA method, respectively.

Multi-Agent Path Finding (MAPF) is an important issue in multi-agent cooperation. Many studies apply MultiAgent Reinforcement Learning (MARL) to solve MAPF in partially observable settings. The objective of cooperative MARL is to maximize the cumulative team reward. Nevertheless, in partially observable settings, the team reward is misleading due to unpredictable factors from the behavior and state of unobserved agents. To address this issue, we propose a Partially Observable Altruistic Q-learning (POAQL) method. POAQL considers the cumulative reward of the observed subteam instead of the whole team, where Altruistic Q-learning plays an important role in learning the subteam action value. In addition, we design a new conflict resolution without additional guidance to emphasize the cooperative nature of MARL frameworks. Experimental results show that POAQL outperforms existing reinforcement learning methods in terms of efficiency and performance.

Trajectory prediction plays a crucial role in autonomous driving, but it is challenging due to the multi-modal nature of future trajectories. Behavior information is frequently employed to capture more diverse modalities of future trajectories. Traditional behavior information is typically hard-encoded, which is often inaccurate and inadequate for reflecting future multimodality. Therefore, we introduce the concept of soft vehicle behavior, which is represented as a probability distribution over a predefined comprehensive set of behaviors. This approach allows for a more rational depiction of vehicle behavior and captures potential future driving modalities. Based on it, we propose a new soft-behavior-constrained vehicle trajectory prediction framework. The framework consists of a backbone and a lightweight and plug-and-play behavior prediction module, which is used to imbue soft behavior constraints to assist in representation learning. We integrated the behavior prediction module into five representative trajectory predictors and achieved improvements of at least 4.2% in minFDE(K=5) on the nuScenes dataset and 0.5% in minFDE(K=6) on the Argoverse 1 motion forecasting dataset. These universal increments prove the effectiveness and generalizability of soft behavior constraints in vehicle trajectory prediction.

We establish a lower bound for the complexity of multiplying two skew polynomials. The lower bound coincides with the upper bound conjectured by Caruso and Borgne in 2017, up to a log factor. We present algorithms for three special cases, indicating that the aforementioned lower bound is quasi-optimal. In fact, our lower bound is also quasi-optimal in the sense of bilinear complexity. In addition, we discuss the average bilinear complexity of simultaneous multiplication of skew polynomials and the complexity of skew polynomial multiplication in the case of towers of extensions.

Significant progress has been made in the field of Instruction-based Image Editing (IIE). However, evaluating these models poses a significant challenge. A crucial requirement in this field is the establishment of a comprehensive evaluation benchmark for accurately assessing editing results and providing valuable insights for its further development. In response to this need, we propose I2EBench, a comprehensive benchmark designed to automatically evaluate the quality of edited images produced by IIE models from multiple dimensions. I2EBench consists of 2,000+ images for editing, along with 4,000+ corresponding original and diverse instructions. It offers three distinctive characteristics: 1) Comprehensive Evaluation Dimensions: I2EBench comprises 16 evaluation dimensions that cover both high-level and low-level aspects, providing a comprehensive assessment of each IIE model. 2) Human Perception Alignment: To ensure the alignment of our benchmark with human perception, we conducted an extensive user study for each evaluation dimension. 3) Valuable Research Insights: By analyzing the advantages and disadvantages of existing IIE models across the 16 dimensions, we offer valuable research insights to guide future development in the field. We will open-source I2EBench, including all instructions, input images, human annotations, edited images from all evaluated methods, and a simple script for evaluating the results from new IIE models. The code, dataset, and generated images from all IIE models are provided in GitHub: https://github.com/cocoshe/I2EBench.

Motion forecasting plays a crucial role in autonomous driving, with the aim of predicting the future reasonable motions of traffic agents. Most existing methods mainly model the historical interactions between agents and the environment, and predict multi-modal trajectories in a feedforward process, ignoring potential trajectory changes caused by future interactions between agents. In this paper, we propose a novel Future Feedback Interaction Network (FFINet) to aggregate the current, observations and potential future interaction features for trajectory prediction. Firstly, we employ different spatial-temporal encoders to embed the decomposed position vectors and the current position of each scene, providing rich features for the subsequent cross-temporal aggregation. Secondly, the relative interaction and cross-temporal aggregation strategies are sequentially adopted to integrate features in the current fusion module, observation interaction module, future feedback module and global fusion module, in which the future feedback module can enable the understanding of pre-action by feeding the influence of preview information to feedforward prediction. Thirdly, the comprehensive interaction features are further fed into final predictor to generate the joint predicted trajectories of multiple agents. Extensive experimental results show that our FFINet achieves the state-of-the-art performance on Argoverse 1 and Argoverse 2 motion forecasting benchmarks.

The asymptotic exponent of matrix multiplication is the smallest ω such that one may multiply two n × n matrices or invert an n × n matrix in O(nω+ε)-complexity for ε > 0 arbitrarily small. One of the biggest open problem in complexity theory and numerical linear algebra is its conjectured value ω = 2. This article is about the universality of ω. We will show that ω is not only the asymptotic exponent for the product operation in matrix algebras but also that for various infinite families of Lie algebras, Jordan algebras, and Clifford algebras. In addition, we will show that ω is not just the asymptotic exponent for matrix product and inversion but also that for the evaluation of any matrix-valued polynomial and rational functions of matrix variables.

We show how the geodesic distance on S++n, the cone of n × n real symmetric or complex Hermitian positive definite matrices regarded as a Riemannian manifold, may be used to naturally define a distance between two such matrices of different dimensions. Given that S++nalso parameterizes n-dimensional ellipsoids, inner products on ℝn, and n × n covariances of nondegenerate probability distributions, this gives us a natural way to define a geometric distance between a pair of such objects of different dimensions.

We present explicit algorithms for computing structured matrix-vector products that are optimal in the sense of Strassen, i.e., using a provably minimum number of multiplications. These structures include Toeplitz/Hankel/circulant, symmetric, Toeplitz-plus-Hankel, sparse, and multilevel structures. The last category include BTTB, BHHB, BCCB but also any arbitrarily complicated nested structures built out of other structures.