This study explores the integration of Agent AI with LangGraph to enhance real-time data analysis systems in big data environments. The proposed framework overcomes limitations of static workflows, inefficient stateful computations, and lack of human intervention by leveraging LangGraph's graph-based workflow construction and dynamic decision-making capabilities. LangGraph allows large language models (LLMs) to dynamically determine control flows, invoke tools, and assess the necessity of further actions, improving flexibility and efficiency. The system architecture incorporates Apache Spark Streaming, Kafka, and LangGraph to create a high-performance sentiment analysis system. LangGraph's capabilities include precise state management, dynamic workflow construction, and robust memory checkpointing, enabling seamless multi-turn interactions and context retention. Human-in-the-loop mechanisms are integrated to refine sentiment analysis, particularly in ambiguous or high-stakes scenarios, ensuring greater reliability and contextual relevance. Key features such as real-time state streaming, debugging via LangGraph Studio, and efficient handling of large-scale data streams make this framework ideal for adaptive decision-making. Experimental results confirm the system's ability to classify inquiries, detect sentiment trends, and escalate complex issues for manual review, demonstrating a synergistic blend of LLM capabilities and human oversight. This work presents a scalable, adaptable, and reliable solution for real-time sentiment analysis and decision-making, advancing the use of Agent AI and LangGraph in big data applications.

This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral thinking queries and evaluation datasets. We introduce Streaming Agentic Lateral Thinking (SALT), a multi-agent framework designed to process complex, low-specificity queries in streaming data environments. SALT implements lateral thinking-inspired System-2 reasoning through a dynamic communication structure between specialized agents. Our key insight is that lateral information flow across long-distance agent interactions, combined with fine-grained belief management, yields richer information contexts and enhanced reasoning. Preliminary quantitative and qualitative evaluations indicate SALT's potential to outperform single-agent systems in handling complex lateral reasoning tasks in a streaming environment.

This paper studies the performative policy learning problem, where agents adjust their features in response to a released policy to improve their potential outcomes, inducing an endogenous distribution shift. There has been growing interest in training machine learning models in strategic environments, including strategic classification and performative prediction. However, existing approaches often rely on restrictive parametric assumptions: micro-level utility models in strategic classification and macro-level data distribution maps in performative prediction, severely limiting scalability and generalizability. We approach this problem as a complex causal inference task, relaxing parametric assumptions on both micro-level agent behavior and macro-level data distribution. Leveraging bounded rationality, we uncover a practical low-dimensional structure in distribution shifts and construct an effective mediator in the causal path from the deployed model to the shifted data. We then propose a gradient-based policy optimization algorithm with a differentiable classifier as a substitute for the high-dimensional distribution map. Our algorithm efficiently utilizes batch feedback and limited manipulation patterns. Our approach achieves high sample efficiency compared to methods reliant on bandit feedback or zero-order optimization. We also provide theoretical guarantees for algorithmic convergence. Extensive and challenging experiments on high-dimensional settings demonstrate our method's practical efficacy.

In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's adaptability across diverse control tasks. At its core, an RL agent seeks to maximize its cumulative reward, enabling AI algorithms to uncover novel solutions previously unknown to experts. However, this focus on reward maximization also introduces a significant difficulty: improper reward specification can result in unexpected, misaligned agent behavior and inefficient learning. The complexity of accurately specifying the reward function is further amplified by the sequential nature of the task, the sparsity of learning signals, and the multifaceted aspects of the desired behavior. In this thesis, we survey the literature on effective reward specification strategies, identify core challenges relating to each of these approaches, and propose original contributions addressing the issue of sample efficiency and alignment in deep reinforcement learning. Reward specification represents one of the most challenging aspects of applying reinforcement learning in real-world domains. Our work underscores the absence of a universal solution to this complex and nuanced challenge; solving it requires selecting the most appropriate tools for the specific requirements of each unique application.

Existing task-oriented AI agents often depend on explicit instructions or external rewards, limiting their ability to be driven by intrinsic motivations like humans. In this paper, we present a desire-driven autonomy framework to guide a Large Language Model-based (LLM-based) agent to simulate human-like daily activities. In contrast to previous agents, our Desire-driven Autonomous Agent (D2A) operates on the principle of intrinsic desire, allowing it to propose and select tasks that fulfill its motivational framework autonomously. Inspired by the Theory of Needs, the motivational framework incorporates an understanding of human-like desires, such as the need for social interaction, personal fulfillment, and self-care. Utilizing a desire-driven task generation mechanism, the agent evaluates its current state and takes a sequence of activities aligned with its intrinsic motivations. Through simulations, we demonstrate that our Desire-driven Autonomous Agent (D2A) generates coherent, contextually relevant daily activities while exhibiting variability and adaptability similar to human behavior. A comparative analysis with other LLM-based frameworks demonstrates that our approach significantly enhances the rationality of the simulated activities.

The card game Hanabi is considered a strong medium for the testing and development of multi-agent reinforcement learning (MARL) algorithms, due to its cooperative nature, hidden information, limited communication and remarkable complexity. Previous research efforts have explored the capabilities of MARL algorithms within Hanabi, focusing largely on advanced architecture design and algorithmic manipulations to achieve state-of-the-art performance for a various number of cooperators. However, this often leads to complex solution strategies with high computational cost and requiring large amounts of training data. For humans to solve the Hanabi game effectively, they require the use of conventions, which often allows for a means to implicitly convey ideas or knowledge based on a predefined, and mutually agreed upon, set of ``rules''. Multi-agent problems containing partial observability, especially when limited communication is present, can benefit greatly from the use of implicit knowledge sharing. In this paper, we propose a novel approach to augmenting the action space using conventions, which act as special cooperative actions that span over multiple time steps and multiple agents, requiring agents to actively opt in for it to reach fruition. These conventions are based on existing human conventions, and result in a significant improvement on the performance of existing techniques for self-play and cross-play across a various number of cooperators within Hanabi.

The rapid evolution of multimodal foundation models has led to significant advancements in cross-modal understanding and generation across diverse modalities, including text, images, audio, and video. However, these models remain susceptible to jailbreak attacks, which can bypass built-in safety mechanisms and induce the production of potentially harmful content. Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications. To provide comprehensive insight into this topic, this survey reviews jailbreak and defense in multimodal generative models. First, given the generalized lifecycle of multimodal jailbreak, we systematically explore attacks and corresponding defense strategies across four levels: input, encoder, generator, and output. Based on this analysis, we present a detailed taxonomy of attack methods, defense mechanisms, and evaluation frameworks specific to multimodal generative models. Additionally, we cover a wide range of input-output configurations, including modalities such as Any-to-Text, Any-to-Vision, and Any-to-Any within generative systems. Finally, we highlight current research challenges and propose potential directions for future research. The open-source repository corresponding to this work can be found at https://github.com/liuxuannan/Awesome-Multimodal-Jailbreak.

In transportation system demand modeling and simulation, agent-based models and microsimulations are current state-of-the-art approaches. However, existing agent-based models still have some limitations on behavioral realism and resource demand that limit their applicability. In this study, leveraging the emerging technology of large language models (LLMs) and LLM-based agents, we propose a general LLM-agent-based modeling framework for transportation systems. We argue that LLM agents not only possess the essential capabilities to function as agents but also offer promising solutions to overcome some limitations of existing agent-based models. Our conceptual framework design closely replicates the decision-making and interaction processes and traits of human travelers within transportation networks, and we demonstrate that the proposed systems can meet critical behavioral criteria for decision-making and learning behaviors using related studies and a demonstrative example of LLM agents' learning and adjustment in the bottleneck setting. Although further refinement of the LLM-agent-based modeling framework is necessary, we believe that this approach has the potential to improve transportation system modeling and simulation.

Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML predictions are used in safety-critical applications, like autonomous cars and surgical robots. Thus, the use of fault tolerance mechanisms, such as safety monitors, is essential to ensure the safe behavior of the system despite the occurrence of faults. This paper presents an extensive literature review on safety monitoring of perception functions using ML in a safety-critical context. In this review, we structure the existing literature to highlight key factors to consider when designing such monitors: threat identification, requirements elicitation, detection of failure, reaction, and evaluation. We also highlight the ongoing challenges associated with safety monitoring and suggest directions for future research.

The incorporation of memory into agents is essential for numerous tasks within the domain of Reinforcement Learning (RL). In particular, memory is paramount for tasks that require the utilization of past information, adaptation to novel environments, and improved sample efficiency. However, the term "memory" encompasses a wide range of concepts, which, coupled with the lack of a unified methodology for validating an agent's memory, leads to erroneous judgments about agents' memory capabilities and prevents objective comparison with other memory-enhanced agents. This paper aims to streamline the concept of memory in RL by providing practical precise definitions of agent memory types, such as long-term versus short-term memory and declarative versus procedural memory, inspired by cognitive science. Using these definitions, we categorize different classes of agent memory, propose a robust experimental methodology for evaluating the memory capabilities of RL agents, and standardize evaluations. Furthermore, we empirically demonstrate the importance of adhering to the proposed methodology when evaluating different types of agent memory by conducting experiments with different RL agents and what its violation leads to. Reinforcement Learning (RL) effectively addresses various problems within the Markov Decision Process (MDP) framework, where agents make decisions based on immediately available information (Mnih et al., 2015; Badia et al., 2020). However, there are still challenges in applying RL to more complex tasks with partial observability. To successfully address such challenges, it is essential that an agent is able to efficiently store and process the history of its interactions with the environment (Ni et al., 2021). Sequence processing methods originally developed for natural language processing (NLP) can be effectively applied to these tasks because the history of interactions with the environment can be represented as a sequence (Hausknecht & Stone, 2015; Esslinger et al., 2022; Samsami et al., 2024). However, in many tasks, due to the complexity or noisiness of observations, the sparsity of events, the difficulty of designing the reward function, and the long duration of episodes, storing and retrieving important information becomes extremely challenging, and the need for memory mechanisms arises (Graves et al., 2016; Wayne et al., 2018; Goyal et al., 2022).