Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities, hold significant potential for TSF. However, existing LLM-based methods usually perform suboptimally because they neglect the inherent characteristics of time series data. Unlike the textual data used in LLM pre-training, the time series data is semantically sparse and comprises distinctive temporal patterns. To address this problem, we propose LLM-PS to empower the LLM for TSF by learning the fundamental \textit{Patterns} and meaningful \textit{Semantics} from time series data. Our LLM-PS incorporates a new multi-scale convolutional neural network adept at capturing both short-term fluctuations and long-term trends within the time series. Meanwhile, we introduce a time-to-text module for extracting valuable semantics across continuous time intervals rather than isolated time points. By integrating these patterns and semantics, LLM-PS effectively models temporal dependencies, enabling a deep comprehension of time series and delivering accurate forecasts. Intensive experimental results demonstrate that LLM-PS achieves state-of-the-art performance in both short- and long-term forecasting tasks, as well as in few- and zero-shot settings.

With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such as memory, tools, environment, and even other agents. However, this advancement has also introduced more complex issues of trustworthiness, which previous research focused solely on LLMs could not cover. In this survey, we propose the TrustAgent framework, a comprehensive study on the trustworthiness of agents, characterized by modular taxonomy, multi-dimensional connotations, and technical implementation. By thoroughly investigating and summarizing newly emerged attacks, defenses, and evaluation methods for agents and MAS, we extend the concept of Trustworthy LLM to the emerging paradigm of Trustworthy Agent. In TrustAgent, we begin by deconstructing and introducing various components of the Agent and MAS. Then, we categorize their trustworthiness into intrinsic (brain, memory, and tool) and extrinsic (user, agent, and environment) aspects. Subsequently, we delineate the multifaceted meanings of trustworthiness and elaborate on the implementation techniques of existing research related to these internal and external modules. Finally, we present our insights and outlook on this domain, aiming to provide guidance for future endeavors.

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the inherent trade-off between computational efficiency and chunking precision in LLM-based approaches, we devise the granularity-aware Mixture-of-Chunkers (MoC) framework, which consists of a three-stage processing mechanism. Notably, our objective is to guide the chunker towards generating a structured list of chunking regular expressions, which are subsequently employed to extract chunks from the original text. Extensive experiments demonstrate that both our proposed metrics and the MoC framework effectively settle challenges of the chunking task, revealing the chunking kernel while enhancing the performance of the RAG system.

As Large Language Models (LLMs) are widely deployed in diverse scenarios, the extent to which they could tacitly spread misinformation emerges as a critical safety concern. Current research primarily evaluates LLMs on explicit false statements, overlooking how misinformation often manifests subtly as unchallenged premises in real-world user interactions. We curated ECHOMIST, the first comprehensive benchmark for implicit misinformation, where the misinformed assumptions are embedded in a user query to LLMs. ECHOMIST is based on rigorous selection criteria and carefully curated data from diverse sources, including real-world human-AI conversations and social media interactions. We also introduce a new evaluation metric to measure whether LLMs can recognize and counter false information rather than amplify users' misconceptions. Through an extensive empirical study on a wide range of LLMs, including GPT-4, Claude, and Llama, we find that current models perform alarmingly poorly on this task, often failing to detect false premises and generating misleading explanations. Our findings underscore the critical need for an increased focus on implicit misinformation in LLM safety research.

Integrating large language models (LLMs) into autonomous driving has attracted significant attention with the hope of improving generalization and explainability. However, existing methods often focus on either driving or vision-language understanding but achieving both high driving performance and extensive language understanding remains challenging. In addition, the dominant approach to tackle vision-language understanding is using visual question answering. However, for autonomous driving, this is only useful if it is aligned with the action space. Otherwise, the model's answers could be inconsistent with its behavior. Therefore, we propose a model that can handle three different tasks: (1) closed-loop driving, (2) vision-language understanding, and (3) language-action alignment. Our model SimLingo is based on a vision language model (VLM) and works using only camera, excluding expensive sensors like LiDAR. SimLingo obtains state-of-the-art performance on the widely used CARLA simulator on the Bench2Drive benchmark and is the winning entry at the CARLA challenge 2024. Additionally, we achieve strong results in a wide variety of language-related tasks while maintaining high driving performance.

We present Auspex - a threat modeling system built using a specialized collection of generative artificial intelligence-based methods that capture threat modeling tradecraft. This new approach, called tradecraft prompting, centers on encoding the on-the-ground knowledge of threat modelers within the prompts that drive a generative AI-based threat modeling system. Auspex employs tradecraft prompts in two processing stages. The first stage centers on ingesting and processing system architecture information using prompts that encode threat modeling tradecraft knowledge pertaining to system decomposition and description. The second stage centers on chaining the resulting system analysis through a collection of prompts that encode tradecraft knowledge on threat identification, classification, and mitigation. The two-stage process yields a threat matrix for a system that specifies threat scenarios, threat types, information security categorizations and potential mitigations. Auspex produces formalized threat model output in minutes, relative to the weeks or months a manual process takes. More broadly, the focus on bespoke tradecraft prompting, as opposed to fine-tuning or agent-based add-ons, makes Auspex a lightweight, flexible, modular, and extensible foundational system capable of addressing the complexity, resource, and standardization limitations of both existing manual and automated threat modeling processes. In this connection, we establish the baseline value of Auspex to threat modelers through an evaluation procedure based on feedback collected from cybersecurity subject matter experts measuring the quality and utility of threat models generated by Auspex on real banking systems. We conclude with a discussion of system performance and plans for enhancements to Auspex.

Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by separating high-level planning from low-level execution, which enables the model to effectively balance high-level planning objectives and low-level execution details. However, generating accurate plans remains difficult since LLMs are not inherently trained for this task. To address this, we propose Plan-and-Act, a novel framework that incorporates explicit planning into LLM-based agents and introduces a scalable method to enhance plan generation through a novel synthetic data generation method. Plan-and-Act consists of a Planner model which generates structured, high-level plans to achieve user goals, and an Executor model that translates these plans into environment-specific actions. To train the Planner effectively, we introduce a synthetic data generation method that annotates ground-truth trajectories with feasible plans, augmented with diverse and extensive examples to enhance generalization. We evaluate Plan-and-Act using web navigation as a representative long-horizon planning environment, demonstrating a state-of the-art 54% success rate on the WebArena-Lite benchmark.

The stability of language model pre-training and its effects on downstream performance are still understudied. Prior work shows that the training process can yield significantly different results in response to slight variations in initial conditions, e.g., the random seed. Crucially, the research community still lacks sufficient resources and tools to systematically investigate pre-training stability, particularly for decoder-only language models. We introduce the PolyPythias, a set of 45 new training runs for the Pythia model suite: 9 new seeds across 5 model sizes, from 14M to 410M parameters, resulting in about 7k new checkpoints that we release. Using these new 45 training runs, in addition to the 5 already available, we study the effects of different initial conditions determined by the seed -- i.e., parameters' initialisation and data order -- on (i) downstream performance, (ii) learned linguistic representations, and (iii) emergence of training phases. In addition to common scaling behaviours, our analyses generally reveal highly consistent training dynamics across both model sizes and initial conditions. Further, the new seeds for each model allow us to identify outlier training runs and delineate their characteristics. Our findings show the potential of using these methods to predict training stability.

Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making in complex 3D environments, which demand second-level responses, high-resolution perception, and tactical reasoning under dynamic conditions. To advance the field, we introduce CombatVLA, an efficient VLA model optimized for combat tasks in 3D action role-playing games(ARPGs). Specifically, our CombatVLA is a 3B model trained on video-action pairs collected by an action tracker, where the data is formatted as action-of-thought (AoT) sequences. Thereafter, CombatVLA seamlessly integrates into an action execution framework, allowing efficient inference through our truncated AoT strategy. Experimental results demonstrate that CombatVLA not only outperforms all existing models on the combat understanding benchmark but also achieves a 50-fold acceleration in game combat. Moreover, it has a higher task success rate than human players. We will open-source all resources, including the action tracker, dataset, benchmark, model weights, training code, and the implementation of the framework at https://combatvla.github.io/.

Post-training plays a crucial role in refining language models, ensuring they exhibit good reasoning capabilities, alignment with ethical and social values, and adaptability to user-specific preferences. Unlike pre-training, which demands extensive computational resources and large-scale datasets, post-training is a more efficient process that leverages targeted fine-tuning techniques such as reinforcement learning from human feedback (RLHF) [1, 2], instruction tuning [3], and Direct Preference Optimization (DPO) [4]. These approaches enable models to generalize better across various tasks and mitigate biases. Furthermore, post-training requires significantly low computational overhead compared to pre-training [5]. Reasoning has long been regarded as a cornerstone in the development of large language models (LLMs).