LLM-based tool agents offer natural language interfaces, enabling users to seamlessly interact with computing services. While REST APIs are valuable resources for building such agents, they must first be transformed into AI-compatible tools. Automatically generating AI-compatible tools from REST API documents can greatly streamline tool agent development and minimize user learning curves. However, API documentation often suffers from a lack of standardization, inconsistent schemas, and incomplete information. To address these issues, we developed \textbf{ToolFactory}, an open-source pipeline for automating tool generation from unstructured API documents. To enhance the reliability of the developed tools, we implemented an evaluation method to diagnose errors. Furthermore, we built a knowledge base of verified tools, which we leveraged to infer missing information from poorly documented APIs. We developed the API Extraction Benchmark, comprising 167 API documents and 744 endpoints in various formats, and designed a JSON schema to annotate them. This annotated dataset was utilized to train and validate ToolFactory. The experimental results highlight the effectiveness of ToolFactory. We also demonstrated ToolFactory by creating a domain-specific AI agent for glycomaterials research. ToolFactory exhibits significant potential for facilitating the seamless integration of scientific REST APIs into AI workflows.
The introduction of new features and services in the banking sector often overwhelms customers, creating an opportunity for banks to enhance user experience through financial chatbots powered by large language models (LLMs). We initiated an AI agent designed to provide customers with relevant information about banking services and insights from annual reports. We proposed a hybrid Customer Analysis Pipeline Retrieval-Augmented Generation (CAPRAG) that effectively addresses both relationship-based and contextual queries, thereby improving customer engagement in the digital banking landscape. To implement this, we developed a processing pipeline to refine text data, which we utilized in two main frameworks: Vector RAG and Graph RAG. This dual approach enables us to populate both vector and graph databases with processed data for efficient retrieval. The Cypher query component is employed to effectively query the graph database. When a user submits a query, it is first expanded by a query expansion module before being routed to construct a final query from the hybrid Knowledge Base (KB). This final query is then sent to an open-source LLM for response generation. Overall, our innovative, designed to international banks, serves bank's customers in an increasingly complex digital environment, enhancing clarity and accessibility of information.
Current financial Large Language Models (LLMs) struggle with two critical limitations: a lack of depth in stock analysis, which impedes their ability to generate professional-grade insights, and the absence of objective evaluation metrics to assess the quality of stock analysis reports. To address these challenges, this paper introduces FinSphere, a conversational stock analysis agent, along with three major contributions: (1) Stocksis, a dataset curated by industry experts to enhance LLMs' stock analysis capabilities, (2) AnalyScore, a systematic evaluation framework for assessing stock analysis quality, and (3) FinSphere, an AI agent that can generate high-quality stock analysis reports in response to user queries. Experiments demonstrate that FinSphere achieves superior performance compared to both general and domain-specific LLMs, as well as existing agent-based systems, even when they are enhanced with real-time data access and few-shot guidance. The integrated framework, which combines real-time data feeds, quantitative tools, and an instruction-tuned LLM, yields substantial improvements in both analytical quality and practical applicability for real-world stock analysis.
Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future. The ability to form and use episodic memories would similarly enable a broad range of improved capabilities in an AI agent that interacts with and takes actions in the world. Researchers have begun directing more attention to developing memory abilities in AI models. It is therefore likely that models with such capability will be become widespread in the near future. This could in some ways contribute to making such AI agents safer by enabling users to better monitor, understand, and control their actions. However, as a new capability with wide applications, we argue that it will also introduce significant new risks that researchers should begin to study and address. We outline these risks and benefits and propose four principles to guide the development of episodic memory capabilities so that these will enhance, rather than undermine, the effort to keep AI safe and trustworthy.
Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factually incorrect. On the other hand, users tend to over-rely on LLM-based AI agents, accepting AI's suggestion even when it is wrong. Adding positive friction, such as explanations or getting user confirmations, has been proposed as a mitigation in AI-supported decision-making systems. In this paper, we propose an accountability model for LLM-based task-oriented dialogue agents to address user overreliance via friction turns in cases of model uncertainty and errors associated with dialogue state tracking (DST). The accountability model is an augmented LLM with an additional accountability head that functions as a binary classifier to predict the relevant slots of the dialogue state mentioned in the conversation. We perform our experiments with multiple backbone LLMs on two established benchmarks (MultiWOZ and Snips). Our empirical findings demonstrate that the proposed approach not only enables reliable estimation of AI agent errors but also guides the decoder in generating more accurate actions. We observe around 3% absolute improvement in joint goal accuracy (JGA) of DST output by incorporating accountability heads into modern LLMs. Self-correcting the detected errors further increases the JGA from 67.13 to 70.51, achieving state-of-the-art DST performance. Finally, we show that error correction through user confirmations (friction turn) achieves a similar performance gain, highlighting its potential to reduce user overreliance.
The rapid deployment of autonomous AI agents creates urgent challenges around authorization, accountability, and access control in digital spaces. New standards are needed to know whom AI agents act on behalf of and guide their use appropriately, protecting online spaces while unlocking the value of task delegation to autonomous agents. We introduce a novel framework for authenticated, authorized, and auditable delegation of authority to AI agents, where human users can securely delegate and restrict the permissions and scope of agents while maintaining clear chains of accountability. This framework builds on existing identification and access management protocols, extending OAuth 2.0 and OpenID Connect with agent-specific credentials and metadata, maintaining compatibility with established authentication and web infrastructure. Further, we propose a framework for translating flexible, natural language permissions into auditable access control configurations, enabling robust scoping of AI agent capabilities across diverse interaction modalities. Taken together, this practical approach facilitates immediate deployment of AI agents while addressing key security and accountability concerns, working toward ensuring agentic AI systems perform only appropriate actions and providing a tool for digital service providers to enable AI agent interactions without risking harm from scalable interaction.
Multimodal AI Agents are AI models that have the capability of interactively and cooperatively assisting human users to solve day-to-day tasks. Augmented Reality (AR) head worn devices can uniquely improve the user experience of solving procedural day-to-day tasks by providing egocentric multimodal (audio and video) observational capabilities to AI Agents. Such AR capabilities can help AI Agents see and listen to actions that users take which can relate to multimodal capabilities of human users. Existing AI Agents, either Large Language Models (LLMs) or Multimodal Vision-Language Models (VLMs) are reactive in nature, which means that models cannot take an action without reading or listening to the human user's prompts. Proactivity of AI Agents on the other hand can help the human user detect and correct any mistakes in agent observed tasks, encourage users when they do tasks correctly or simply engage in conversation with the user - akin to a human teaching or assisting a user. Our proposed YET to Intervene (YETI) multimodal agent focuses on the research question of identifying circumstances that may require the agent to intervene proactively. This allows the agent to understand when it can intervene in a conversation with human users that can help the user correct mistakes on tasks, like cooking, using AR. Our YETI Agent learns scene understanding signals based on interpretable notions of Structural Similarity (SSIM) on consecutive video frames. We also define the alignment signal which the AI Agent can learn to identify if the video frames corresponding to the user's actions on the task are consistent with expected actions. These signals are used by our AI Agent to determine when it should proactively intervene. We compare our results on the instances of proactive intervention in the HoloAssist multimodal benchmark for an expert agent guiding a user to complete procedural tasks.
Despite significant advancements in general-purpose AI agents, several challenges still hinder their practical application in real-world scenarios. First, the limited planning capabilities of Large Language Models (LLM) restrict AI agents from effectively solving complex tasks that require long-horizon planning. Second, general-purpose AI agents struggle to efficiently utilize domain-specific knowledge and human expertise. In this paper, we introduce the Standard Operational Procedure-guided Agent (SOP-agent), a novel framework for constructing domain-specific agents through pseudocode-style Standard Operational Procedures (SOPs) written in natural language. Formally, we represent a SOP as a decision graph, which is traversed to guide the agent in completing tasks specified by the SOP. We conduct extensive experiments across tasks in multiple domains, including decision-making, search and reasoning, code generation, data cleaning, and grounded customer service. The SOP-agent demonstrates excellent versatility, achieving performance superior to general-purpose agent frameworks and comparable to domain-specific agent systems. Additionally, we introduce the Grounded Customer Service Benchmark, the first benchmark designed to evaluate the grounded decision-making capabilities of AI agents in customer service scenarios based on SOPs.
The proliferation of misinformation on social media platforms has highlighted the need to understand how individual personality traits influence susceptibility to and propagation of misinformation. This study employs an innovative agent-based modeling approach to investigate the relationship between personality traits and misinformation dynamics. Using six AI agents embodying different dimensions of the Big Five personality traits (Extraversion, Agreeableness, and Neuroticism), we simulated interactions across six diverse misinformation topics. The experiment, implemented through the AgentScope framework using the GLM-4-Flash model, generated 90 unique interactions, revealing complex patterns in how personality combinations affect persuasion and resistance to misinformation. Our findings demonstrate that analytical and critical personality traits enhance effectiveness in evidence-based discussions, while non-aggressive persuasion strategies show unexpected success in misinformation correction. Notably, agents with critical traits achieved a 59.4% success rate in HIV-related misinformation discussions, while those employing non-aggressive approaches maintained consistent persuasion rates above 40% across different personality combinations. The study also revealed a non-transitive pattern in persuasion effectiveness, challenging conventional assumptions about personality-based influence. These results provide crucial insights for developing personality-aware interventions in digital environments and suggest that effective misinformation countermeasures should prioritize emotional connection and trust-building over confrontational approaches. The findings contribute to both theoretical understanding of personality-misinformation dynamics and practical strategies for combating misinformation in social media contexts.
AI Agent, powered by large language models (LLMs) as its cognitive core, is an intelligent agentic system capable of autonomously controlling and determining the execution paths under user's instructions. With the burst of capabilities of LLMs and various plugins, such as RAG, text-to-image/video/3D, etc., the potential of AI Agents has been vastly expanded, with their capabilities growing stronger by the day. However, at the intersection between AI and web3, there is currently no ideal agentic framework that can seamlessly integrate web3 applications into AI agent functionalities. In this paper, we propose Eliza, the first open-source web3-friendly Agentic framework that makes the deployment of web3 applications effortless. We emphasize that every aspect of Eliza is a regular Typescript program under the full control of its user, and it seamlessly integrates with web3 (i.e., reading and writing blockchain data, interacting with smart contracts, etc.). Furthermore, we show how stable performance is achieved through the pragmatic implementation of the key components of Eliza's runtime. Our code is publicly available at https://github.com/ai16z/eliza.
The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm; however, without careful design of reward functions, agents can learn to solve problems in ways that may be considered "undesirable" or "unethical." Without thorough understanding of the incentives a reward function creates, it can be difficult to impose principled yet general control mechanisms over its behavior. In this paper, we study methods for constructing guardrails for AI agents that use reward functions to learn decision making. We introduce a novel approach, which we call strategy masking, to explicitly learn and then suppress undesirable AI agent behavior. We apply our method to study lying in AI agents and show that it can be used to effectively modify agent behavior by suppressing lying post-training without compromising agent ability to perform effectively.
In the vast domain of cybersecurity, the transition from reactive defense to offensive has become critical in protecting digital infrastructures. This paper explores the integration of Artificial Intelligence (AI) into offensive cybersecurity, particularly through the development of an autonomous AI agent, ReaperAI, designed to simulate and execute cyberattacks. Leveraging the capabilities of Large Language Models (LLMs) such as GPT-4, ReaperAI demonstrates the potential to identify, exploit, and analyze security vulnerabilities autonomously. This research outlines the core methodologies that can be utilized to increase consistency and performance, including task-driven penetration testing frameworks, AI-driven command generation, and advanced prompting techniques. The AI agent operates within a structured environment using Python, enhanced by Retrieval Augmented Generation (RAG) for contextual understanding and memory retention. ReaperAI was tested on platforms including, Hack The Box, where it successfully exploited known vulnerabilities, demonstrating its potential power. However, the deployment of AI in offensive security presents significant ethical and operational challenges. The agent's development process revealed complexities in command execution, error handling, and maintaining ethical constraints, highlighting areas for future enhancement. This study contributes to the discussion on AI's role in cybersecurity by showcasing how AI can augment offensive security strategies. It also proposes future research directions, including the refinement of AI interactions with cybersecurity tools, enhancement of learning mechanisms, and the discussion of ethical guidelines for AI in offensive roles. The findings advocate for a unique approach to AI implementation in cybersecurity, emphasizing innovation.
With over 85 million CT scans performed annually in the United States, creating tumor-related reports is a challenging and time-consuming task for radiologists. To address this need, we present RadGPT, an Anatomy-Aware Vision-Language AI Agent for generating detailed reports from CT scans. RadGPT first segments tumors, including benign cysts and malignant tumors, and their surrounding anatomical structures, then transforms this information into both structured reports and narrative reports. These reports provide tumor size, shape, location, attenuation, volume, and interactions with surrounding blood vessels and organs. Extensive evaluation on unseen hospitals shows that RadGPT can produce accurate reports, with high sensitivity/specificity for small tumor (<2 cm) detection: 80/73% for liver tumors, 92/78% for kidney tumors, and 77/77% for pancreatic tumors. For large tumors, sensitivity ranges from 89% to 97%. The results significantly surpass the state-of-the-art in abdominal CT report generation. RadGPT generated reports for 17 public datasets. Through radiologist review and refinement, we have ensured the reports' accuracy, and created the first publicly available image-text 3D medical dataset, comprising over 1.8 million text tokens and 2.7 million images from 9,262 CT scans, including 2,947 tumor scans/reports of 8,562 tumor instances. Our reports can: (1) localize tumors in eight liver sub-segments and three pancreatic sub-segments annotated per-voxel; (2) determine pancreatic tumor stage (T1-T4) in 260 reports; and (3) present individual analyses of multiple tumors--rare in human-made reports. Importantly, 948 of the reports are for early-stage tumors.
This paper discusses the use of Artificial Intelligence (AI) to enhance workplace productivity and employee well-being. By integrating machine learning (ML) techniques with neurobiological data, the proposed approaches ensure alignment with human ethical standards through value alignment models and Hierarchical Reinforcement Learning (HRL) for autonomous task management. The system utilizes biometric feedback from employees to generate personalized health prompts, fostering a supportive work environment that encourages physical activity. Additionally, we explore decentralized multi-agent systems for improved collaboration and decision-making frameworks that enhance transparency. Various approaches using ML techniques in conjunction with AI implementations are discussed. Together, these innovations aim to create a more productive and health-conscious workplace. These outcomes assist HR management and organizations in launching more rational career progression streams for employees and facilitating organizational transformation.
The development of large language models has ushered in new paradigms for education. This paper centers on the multi-Agent system in education and proposes the von Neumann multi-Agent system framework. It breaks down each AI Agent into four modules: control unit, logic unit, storage unit, and input-output devices, defining four types of operations: task deconstruction, self-reflection, memory processing, and tool invocation. Furthermore, it introduces related technologies such as Chain-of-Thought, Reson+Act, and Multi-Agent Debate associated with these four types of operations. The paper also discusses the ability enhancement cycle of a multi-Agent system for education, including the outer circulation for human learners to promote knowledge construction and the inner circulation for LLM-based-Agents to enhance swarm intelligence. Through collaboration and reflection, the multi-Agent system can better facilitate human learners' learning and enhance their teaching abilities in this process.
Large Language Models (LLMs) based agents are transforming the programming language landscape by facilitating learning for beginners, enabling code generation, and optimizing documentation workflows. Hardware Description Languages (HDLs), with their smaller user community, stand to benefit significantly from the application of LLMs as tools for learning new HDLs. This paper investigates the challenges and solutions of enabling LLMs for HDLs, particularly for HDLs that LLMs have not been previously trained on. This work introduces HDLAgent, an AI agent optimized for LLMs with limited knowledge of various HDLs. It significantly enhances off-the-shelf LLMs.
This work investigates the causal mechanism behind the effect of chatbot personification and persuasion strategies on users' perceptions and donation likelihood. In a 2 (personified vs. non-personified chatbot) x 2 (emotional vs. logical persuasion strategy) between-subjects experiment (N=76), participants engaged with a chatbot that represented a non-profit charitable organization. The results suggest that interaction with a personified chatbot evokes perceived anthropomorphism; however, it does not elicit greater willingness to donate. In fact, we found that commonly used anthropomorphic features, like name and narrative, led to negative attitudes toward an AI agent in the donation context. Our results showcase a preference for non-personified chatbots paired with logical persuasion appeal, emphasizing the significance of consistency in chatbot interaction, mirroring human-human engagement. We discuss the importance of moving from exploring the common scenario of a chatbot with machine identity vs. a chatbot with human identity in light of the recent regulations of AI systems.
Minecraft has emerged as a valuable testbed for embodied intelligence and sequential decision-making research, yet the development and validation of novel agents remains hindered by significant engineering challenges. This paper presents MineStudio, an open-source software package designed to streamline embodied policy development in Minecraft. MineStudio represents the first comprehensive integration of seven critical engineering components: simulator, data, model, offline pretraining, online finetuning, inference, and benchmark, thereby allowing users to concentrate their efforts on algorithm innovation. We provide a user-friendly API design accompanied by comprehensive documentation and tutorials. The complete codebase is publicly available at https://github.com/CraftJarvis/MineStudio.
Surveys and interviews are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. Recently, various domains have begun to explore the use of conversational agents (chatbots) powered by generative artificial intelligence (AI) technologies. However, considering decisions in transportation investments and policies often carry significant public and environmental stakes, surveys and interviews face unique challenges in integrating AI agents, underscoring the need for a rigorous, resource-efficient approach that enhances participant engagement and ensures privacy. This paper addresses this gap by introducing a modular approach and its resulting parameterized process for designing AI agents. We detail the system architecture, integrating engineered prompts, specialized knowledge bases, and customizable, goal-oriented conversational logic. We demonstrate the adaptability, generalizability, and efficacy of our modular approach through three empirical studies: (1) travel preference surveys, highlighting conditional logic and multimodal (voice, text, and image generation) capabilities; (2) public opinion elicitation on a newly constructed, novel infrastructure project, showcasing question customization and multilingual (English and French) capabilities; and (3) expert consultation about the impact of technologies on future transportation systems, highlighting real-time, clarification request capabilities for open-ended questions, resilience in handling erratic inputs, and efficient transcript postprocessing. The results suggest that the AI agent increases completion rates and response quality. Furthermore, the modular approach demonstrates controllability, flexibility, and robustness while addressing key ethical, privacy, security, and token consumption concerns.
AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic. This paper addresses a challenging and under-explored problem: a deployed AI agent that continuously encounters unlabeled data - which may include both unseen samples of known classes and samples from novel (unknown) classes - and must adapt to it continuously. To tackle this challenge, we propose our method COUQ "Continual Open-world Uncertainty Quantification", an iterative uncertainty estimation algorithm tailored for learning in generalized continual open-world multi-class settings. We rigorously apply and evaluate COUQ on key sub-tasks in the Continual Open-World: continual novelty detection, uncertainty guided active learning, and uncertainty guided pseudo-labeling for semi-supervised CL. We demonstrate the effectiveness of our method across multiple datasets, ablations, backbones and performance superior to state-of-the-art.