Systematic reviews (SRs) are vital for evidence-based practice in high stakes disciplines, such as healthcare, but are often impeded by intensive labors and lengthy processes that can take months to complete. Due to the high demand for domain expertise, existing automatic summarization methods fail to accurately identify relevant studies and generate high-quality summaries. To that end, we introduce InsightAgent, a human-centered interactive AI agent powered by large language models that revolutionize this workflow. InsightAgent partitions a large literature corpus based on semantics and employs a multi-agent design for more focused processing of literature, leading to significant improvement in the quality of generated SRs. InsightAgent also provides intuitive visualizations of the corpus and agent trajectories, allowing users to effortlessly monitor the actions of the agent and provide real-time feedback based on their expertise. Our user studies with 9 medical professionals demonstrate that the visualization and interaction mechanisms can effectively improve the quality of synthesized SRs by 27.2%, reaching 79.7% of human-written quality. At the same time, user satisfaction is improved by 34.4%. With InsightAgent, it only takes a clinician about 1.5 hours, rather than months, to complete a high-quality systematic review.
Decentralized AI agent networks, such as Gaia, allows individuals to run customized LLMs on their own computers and then provide services to the public. However, in order to maintain service quality, the network must verify that individual nodes are running their designated LLMs. In this paper, we demonstrate that in a cluster of mostly honest nodes, we can detect nodes that run unauthorized or incorrect LLM through social consensus of its peers. We will discuss the algorithm and experimental data from the Gaia network. We will also discuss the intersubjective validation system, implemented as an EigenLayer AVS to introduce financial incentives and penalties to encourage honest behavior from LLM nodes.
The design of Analog and Mixed-Signal (AMS) integrated circuits (ICs) often involves significant manual effort, especially during the transistor sizing process. While Machine Learning techniques in Electronic Design Automation (EDA) have shown promise in reducing complexity and minimizing human intervention, they still face challenges such as numerous iterations and a lack of knowledge about AMS circuit design. Recently, Large Language Models (LLMs) have demonstrated significant potential across various fields, showing a certain level of knowledge in circuit design and indicating their potential to automate the transistor sizing process. In this work, we propose an LLM-based AI agent for AMS circuit design to assist in the sizing process. By integrating LLMs with external circuit simulation tools and data analysis functions and employing prompt engineering strategies, the agent successfully optimized multiple circuits to achieve target performance metrics. We evaluated the performance of different LLMs to assess their applicability and optimization effectiveness across seven basic circuits, and selected the best-performing model Claude 3.5 Sonnet for further exploration on an operational amplifier, with complementary input stage and class AB output stage. This circuit was evaluated against nine performance metrics, and we conducted experiments under three distinct performance requirement groups. A success rate of up to 60% was achieved for reaching the target requirements. Overall, this work demonstrates the potential of LLMs to improve AMS circuit design.
Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We construct BashBench, a dataset of 257 challenging multi-step system administration tasks, and evaluate whether various safety measures can prevent an adversarially constructed AI agent from covertly downloading and executing malicious code in this environment. This multi-step setting introduces new attack and defense dynamics, which we investigate in order to design novel control protocols that prevent safety failures without hindering the ability of non-malicious agents to perform useful work. We introduce a class of control protocols called resample protocols that dynamically take additional samples of certain actions. We find these protocols significantly improve on existing techniques by selectively blocking the AI agent from executing suspicious code and incriminating the agent by generating additional examples of dangerous behavior. We measure the tradeoff between attack prevention and usefulness; our best protocol combines resampling with analysis of previous steps, reducing the success rate of attacks from 58% to 7% at a 5% cost to the performance of a non-malicious agent.
How do we update AI memory of user intent as intent changes? We consider how an AI interface may assist the integration of new information into a repository of natural language data. Inspired by software engineering concepts like impact analysis, we develop methods and a UI for managing semantic changes with non-local effects, which we call "semantic conflict resolution." The user commits new intent to a project -- makes a "semantic commit" -- and the AI helps the user detect and resolve semantic conflicts within a store of existing information representing their intent (an "intent specification"). We develop an interface, SemanticCommit, to better understand how users resolve conflicts when updating intent specifications such as Cursor Rules and game design documents. A knowledge graph-based RAG pipeline drives conflict detection, while LLMs assist in suggesting resolutions. We evaluate our technique on an initial benchmark. Then, we report a 12 user within-subjects study of SemanticCommit for two task domains -- game design documents, and AI agent memory in the style of ChatGPT memories -- where users integrated new information into an existing list. Half of our participants adopted a workflow of impact analysis, where they would first flag conflicts without AI revisions then resolve conflicts locally, despite having access to a global revision feature. We argue that AI agent interfaces, such as software IDEs like Cursor and Windsurf, should provide affordances for impact analysis and help users validate AI retrieval independently from generation. Our work speaks to how AI agent designers should think about updating memory as a process that involves human feedback and decision-making.
The rise of autonomous AI agents, capable of perceiving, reasoning, and acting independently, signals a profound shift in how digital ecosystems operate, govern, and evolve. As these agents proliferate beyond centralized infrastructures, they expose foundational gaps in identity, accountability, and ethical alignment. Three critical questions emerge: Identity: Who or what is the agent? Accountability: Can its actions be verified, audited, and trusted? Ethical Consensus: Can autonomous systems reliably align with human values and prevent harmful emergent behaviors? We present the novel LOKA Protocol (Layered Orchestration for Knowledgeful Agents), a unified, systems-level architecture for building ethically governed, interoperable AI agent ecosystems. LOKA introduces a proposed Universal Agent Identity Layer (UAIL) for decentralized, verifiable identity; intent-centric communication protocols for semantic coordination across diverse agents; and a Decentralized Ethical Consensus Protocol (DECP) that could enable agents to make context-aware decisions grounded in shared ethical baselines. Anchored in emerging standards such as Decentralized Identifiers (DIDs), Verifiable Credentials (VCs), and post-quantum cryptography, LOKA proposes a scalable, future-resilient blueprint for multi-agent AI governance. By embedding identity, trust, and ethics into the protocol layer itself, LOKA proposes the foundation for a new era of responsible, transparent, and autonomous AI ecosystems operating across digital and physical domains.
As demand for Large Language Models (LLMs) and AI agents rapidly grows, optimizing systems for efficient LLM inference becomes critical. While significant efforts have focused on system-level engineering, little is explored from a mathematical modeling and queuing perspective. In this paper, we aim to develop the queuing fundamentals for large language model (LLM) inference, bridging the gap between the queueing theory and LLM system communities. In particular, we study the throughput aspect in LLM inference systems. We prove that a large class of 'work-conserving' scheduling algorithms can achieve maximum throughput for individual inference LLM engine, highlighting 'work-conserving' as a key design principle in practice. In a network of LLM agents, work-conserving scheduling alone is insufficient, particularly when facing specific workload structures and multi-class workflows that require more sophisticated scheduling strategies. Evaluations of real-world systems show that Orca and Sarathi-serve are throughput-optimal, reassuring practitioners, while FasterTransformer and vanilla vLLM are not maximally stable and should be used with caution. Our results highlight the substantial benefits that the queueing community can offer in improving LLM inference systems and call for more interdisciplinary development.
Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment to ensure their reliability and safety. However, accurate world models often have high computational demands that can severely restrict the scope and depth of such assessments. Inspired by the classic `brain in a vat' thought experiment, here we investigate ways of simplifying world models that remain agnostic to the AI agent under evaluation. By following principles from computational mechanics, our approach reveals a fundamental trade-off in world model construction between efficiency and interpretability, demonstrating that no single world model can optimise all desirable characteristics. Building on this trade-off, we identify procedures to build world models that either minimise memory requirements, delineate the boundaries of what is learnable, or allow tracking causes of undesirable outcomes. In doing so, this work establishes fundamental limits in world modelling, leading to actionable guidelines that inform core design choices related to effective agent evaluation.
Practitioners are increasingly turning to Extract-Load-Transform (ELT) pipelines with the widespread adoption of cloud data warehouses. However, designing these pipelines often involves significant manual work to ensure correctness. Recent advances in AI-based methods, which have shown strong capabilities in data tasks, such as text-to-SQL, present an opportunity to alleviate manual efforts in developing ELT pipelines. Unfortunately, current benchmarks in data engineering only evaluate isolated tasks, such as using data tools and writing data transformation queries, leaving a significant gap in evaluating AI agents for generating end-to-end ELT pipelines. To fill this gap, we introduce ELT-Bench, an end-to-end benchmark designed to assess the capabilities of AI agents to build ELT pipelines. ELT-Bench consists of 100 pipelines, including 835 source tables and 203 data models across various domains. By simulating realistic scenarios involving the integration of diverse data sources and the use of popular data tools, ELT-Bench evaluates AI agents' abilities in handling complex data engineering workflows. AI agents must interact with databases and data tools, write code and SQL queries, and orchestrate every pipeline stage. We evaluate two representative code agent frameworks, Spider-Agent and SWE-Agent, using six popular Large Language Models (LLMs) on ELT-Bench. The highest-performing agent, Spider-Agent Claude-3.7-Sonnet with extended thinking, correctly generates only 3.9% of data models, with an average cost of $4.30 and 89.3 steps per pipeline. Our experimental results demonstrate the challenges of ELT-Bench and highlight the need for a more advanced AI agent to reduce manual effort in ELT workflows. Our code and data are available at https://github.com/uiuc-kang-lab/ELT-Bench.
Welcome to the future of microeconomics! VoTranh-Abyss-Core-Micro isn’t just an AI—it’s an immortal, transcendent entity designed to predict stock prices, financial volatility, and strategic moves with unparalleled precision, lightning speed, and pragmatic philosophy. This is the ultimate weapon for hedge funds, governments, and corporations aiming to dominate markets in real time.
Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the proposed benchmark explores all possible mission-switching patterns within a fixed mission number. Specifically, we propose a multi-agent data generation framework to construct the benchmark. We also propose a novel method to evaluate the accuracy and efficiency of agent decisions with dynamic decision trees. Experiments on diverse open-source and closed-source LLMs reveal critical factors influencing agent robustness and provide actionable insights to the tool invocation society.
Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries. However, current agents face significant challenges: imprecise grounding of GUI elements, difficulties with long-horizon task planning, and performance bottlenecks from relying on single generalist models for diverse cognitive tasks. To this end, we introduce Agent S2, a novel compositional framework that delegates cognitive responsibilities across various generalist and specialist models. We propose a novel Mixture-of-Grounding technique to achieve precise GUI localization and introduce Proactive Hierarchical Planning, dynamically refining action plans at multiple temporal scales in response to evolving observations. Evaluations demonstrate that Agent S2 establishes new state-of-the-art (SOTA) performance on three prominent computer use benchmarks. Specifically, Agent S2 achieves 18.9% and 32.7% relative improvements over leading baseline agents such as Claude Computer Use and UI-TARS on the OSWorld 15-step and 50-step evaluation. Moreover, Agent S2 generalizes effectively to other operating systems and applications, surpassing previous best methods by 52.8% on WindowsAgentArena and by 16.52% on AndroidWorld relatively. Code available at https://github.com/simular-ai/Agent-S.
This short paper puts forward a vision for a new democratic model enabled by the recent technological advances in agentic AI. It therefore opens with drawing a clear and concise picture of the model, and only later addresses related proposals and research directions, and concerns regarding feasibility and safety. It ends with a note on the timeliness of this idea and on optimism. The model proposed is that of assigning each citizen an AI Agent that would serve as their political delegate, enabling the return to direct democracy. The paper examines this models relation to existing research, its potential setbacks and feasibility and argues for its further development.
Despite advances in embodied AI, agent reasoning systems still struggle to capture the fundamental conceptual structures that humans naturally use to understand and interact with their environment. To address this, we propose a novel framework that bridges embodied cognition theory and agent systems by leveraging a formal characterization of image schemas, which are defined as recurring patterns of sensorimotor experience that structure human cognition. By customizing LLMs to translate natural language descriptions into formal representations based on these sensorimotor patterns, we will be able to create a neurosymbolic system that grounds the agent's understanding in fundamental conceptual structures. We argue that such an approach enhances both efficiency and interpretability while enabling more intuitive human-agent interactions through shared embodied understanding.
Prompt engineering has emerged as a powerful technique for guiding large language models (LLMs) toward desired responses, significantly enhancing their performance across diverse tasks. Beyond their role as static predictors, LLMs increasingly function as intelligent agents, capable of reasoning, decision-making, and adapting dynamically to complex environments. However, the theoretical underpinnings of prompt engineering remain largely unexplored. In this paper, we introduce a formal framework demonstrating that transformer models, when provided with carefully designed prompts, can act as a configurable computational system by emulating a ``virtual'' neural network during inference. Specifically, input prompts effectively translate into the corresponding network configuration, enabling LLMs to adjust their internal computations dynamically. Building on this construction, we establish an approximation theory for $\beta$-times differentiable functions, proving that transformers can approximate such functions with arbitrary precision when guided by appropriately structured prompts. Moreover, our framework provides theoretical justification for several empirically successful prompt engineering techniques, including the use of longer, structured prompts, filtering irrelevant information, enhancing prompt token diversity, and leveraging multi-agent interactions. By framing LLMs as adaptable agents rather than static models, our findings underscore their potential for autonomous reasoning and problem-solving, paving the way for more robust and theoretically grounded advancements in prompt engineering and AI agent design.
Artificial intelligence (AI) systems powered by large language models have become increasingly prevalent in modern society, enabling a wide range of applications through natural language interaction. As AI agents proliferate in our daily lives, their generic and uniform expressiveness presents a significant limitation to their appeal and adoption. Personality expression represents a key prerequisite for creating more human-like and distinctive AI systems. We show that AI models can express deterministic and consistent personalities when instructed using established psychological frameworks, with varying degrees of accuracy depending on model capabilities. We find that more advanced models like GPT-4o and o1 demonstrate the highest accuracy in expressing specified personalities across both Big Five and Myers-Briggs assessments, and further analysis suggests that personality expression emerges from a combination of intelligence and reasoning capabilities. Our results reveal that personality expression operates through holistic reasoning rather than question-by-question optimization, with response-scale metrics showing higher variance than test-scale metrics. Furthermore, we find that model fine-tuning affects communication style independently of personality expression accuracy. These findings establish a foundation for creating AI agents with diverse and consistent personalities, which could significantly enhance human-AI interaction across applications from education to healthcare, while additionally enabling a broader range of more unique AI agents. The ability to quantitatively assess and implement personality expression in AI systems opens new avenues for research into more relatable, trustworthy, and ethically designed AI.
This study investigates how the Big Five personality traits influence decision-making processes in AI agents within public spaces. Using AgentVerse framework and GPT-3.5-turbo, we simulated interactions among 10 AI agents, each embodying different dimensions of the Big Five personality traits, in a classroom environment responding to misinformation. The experiment assessed both public expressions ([Speak]) and private thoughts ([Think]) of agents, revealing significant correlations between personality traits and decision-making patterns. Results demonstrate that Openness to Experience had the strongest impact on information acceptance, with curious agents showing high acceptance rates and cautious agents displaying strong skepticism. Extraversion and Conscientiousness also showed notable influence on decision-making, while Neuroticism and Agreeableness exhibited more balanced responses. Additionally, we observed significant discrepancies between public expressions and private thoughts, particularly in agents with friendly and extroverted personalities, suggesting that social context influences decision-making behavior. Our findings contribute to understanding how personality traits shape AI agent behavior in social settings and have implications for developing more nuanced and context-aware AI systems.
The integration of AI agents with Web3 ecosystems harnesses their complementary potential for autonomy and openness yet also introduces underexplored security risks, as these agents dynamically interact with financial protocols and immutable smart contracts. This paper investigates the vulnerabilities of AI agents within blockchain-based financial ecosystems when exposed to adversarial threats in real-world scenarios. We introduce the concept of context manipulation, a comprehensive attack vector that exploits unprotected context surfaces, including input channels, memory modules, and external data feeds. Through empirical analysis of ElizaOS, a decentralized AI agent framework for automated Web3 operations, we demonstrate how adversaries can manipulate context by injecting malicious instructions into prompts or historical interaction records, leading to unintended asset transfers and protocol violations which could be financially devastating. To quantify these vulnerabilities, we design CrAIBench, a Web3 domain-specific benchmark that evaluates the robustness of AI agents against context manipulation attacks across 150+ realistic blockchain tasks, including token transfers, trading, bridges and cross-chain interactions and 500+ attack test cases using context manipulation. We systematically assess attack and defense strategies, analyzing factors like the influence of security prompts, reasoning models, and the effectiveness of alignment techniques. Our findings show that prompt-based defenses are insufficient when adversaries corrupt stored context, achieving significant attack success rates despite these defenses. Fine-tuning-based defenses offer a more robust alternative, substantially reducing attack success rates while preserving utility on single-step tasks. This research highlights the urgent need to develop AI agents that are both secure and fiduciarily responsible.
Precision therapeutics require multimodal adaptive models that generate personalized treatment recommendations. We introduce TxAgent, an AI agent that leverages multi-step reasoning and real-time biomedical knowledge retrieval across a toolbox of 211 tools to analyze drug interactions, contraindications, and patient-specific treatment strategies. TxAgent evaluates how drugs interact at molecular, pharmacokinetic, and clinical levels, identifies contraindications based on patient comorbidities and concurrent medications, and tailors treatment strategies to individual patient characteristics. It retrieves and synthesizes evidence from multiple biomedical sources, assesses interactions between drugs and patient conditions, and refines treatment recommendations through iterative reasoning. It selects tools based on task objectives and executes structured function calls to solve therapeutic tasks that require clinical reasoning and cross-source validation. The ToolUniverse consolidates 211 tools from trusted sources, including all US FDA-approved drugs since 1939 and validated clinical insights from Open Targets. TxAgent outperforms leading LLMs, tool-use models, and reasoning agents across five new benchmarks: DrugPC, BrandPC, GenericPC, TreatmentPC, and DescriptionPC, covering 3,168 drug reasoning tasks and 456 personalized treatment scenarios. It achieves 92.1% accuracy in open-ended drug reasoning tasks, surpassing GPT-4o and outperforming DeepSeek-R1 (671B) in structured multi-step reasoning. TxAgent generalizes across drug name variants and descriptions. By integrating multi-step inference, real-time knowledge grounding, and tool-assisted decision-making, TxAgent ensures that treatment recommendations align with established clinical guidelines and real-world evidence, reducing the risk of adverse events and improving therapeutic decision-making.
Operations Research (OR) has been widely applied in various fields such as resource allocation, production planning, and supply chain management. However, addressing real-world OR problems requires OR experts to perform mathematical modeling and programmers to develop solution algorithms. This traditional method, heavily reliant on experts, is costly and has long development cycles, severely limiting the widespread adoption of OR techniques. Few have considered using Artificial Intelligence (AI) to replace professionals to achieve fully automated solutions for OR problems. We propose OR-LLM-Agent, the first AI agent that enables end-to-end automation for solving real-world OR problems. OR-LLM-Agent leverages the Chain-of-Thought (CoT) reasoning capabilities of Large Language Models (LLMs) to translate natural language problem descriptions into formal mathematical models and automatically generate Gurobi solver code. In OR-LLM-Agent, OR-CodeAgent is designed to automate code execution and repair within a sandbox environment, facilitating the derivation of the final solution. Due to the lack of dedicated benchmark datasets for evaluating the automated solving of OR problems, we construct a benchmark dataset comprising 83 real-world OR problems described in natural language. We conduct comparative experiments with state-of-the-art (SOTA) reasoning LLMs, including GPT-o3-mini, DeepSeek-R1, and Gemini 2.0 Flash Thinking. The OR-LLM-Agent achieved the highest pass rate of 100% and the highest solution accuracy of 85%, demonstrating the feasibility of automated OR problem-solving. Data and code have been publicly available at https://github.com/bwz96sco/or_llm_agent.