Decentralized multi-agent systems have shown promise in enabling autonomous collaboration among LLM-based agents. While AgentNet demonstrated the feasibility of fully decentralized coordination through dynamic DAG topologies, several limitations remain: scalability challenges with large agent populations, communication overhead, lack of privacy guarantees, and suboptimal resource allocation. We propose AgentNet++, a hierarchical decentralized framework that extends AgentNet with multilevel agent organization, privacy-preserving knowledge sharing via differential privacy and secure aggregation, adaptive resource management, and theoretical convergence guarantees. Our approach introduces cluster-based hierarchies where agents self-organize into specialized groups, enabling efficient task routing and knowledge distillation while maintaining full decentralization. We provide formal analysis of convergence properties and privacy bounds, and demonstrate through extensive experiments on complex multi-agent tasks that AgentNet++ achieves 23% higher task completion rates, 40% reduction in communication overhead, and maintains strong privacy guarantees compared to AgentNet and other baselines.

This paper presents a novel, structured decision support framework that systematically aligns diverse artificial intelligence (AI) agent architectures, reactive, cognitive, hybrid, and learning, with the comprehensive National Institute of Standards and Technology (NIST) Cybersecurity Framework (CSF) 2.0. By integrating agent theory with industry guidelines, this framework provides a transparent and stepwise methodology for selecting and deploying AI solutions to address contemporary cyber threats. Employing a granular decomposition of NIST CSF 2.0 functions into specific tasks, the study links essential AI agent properties such as autonomy, adaptive learning, and real-time responsiveness to each subcategory's security requirements. In addition, it outlines graduated levels of autonomy (assisted, augmented, and fully autonomous) to accommodate organisations at varying stages of cybersecurity maturity. This holistic approach transcends isolated AI applications, providing a unified detection, incident response, and governance strategy. Through conceptual validation, the framework demonstrates how tailored AI agent deployments can align with real-world constraints and risk profiles, enhancing situational awareness, accelerating response times, and fortifying long-term resilience via adaptive risk management. Ultimately, this research bridges the gap between theoretical AI constructs and operational cybersecurity demands, establishing a foundation for robust, empirically validated multi-agent systems that adhere to industry standards.

Enterprise AI deployment faces critical "Know Your Agent" (KYA) challenges where organizations must verify third-party agent capabilities and establish trust without standardized metadata or verification infrastructure. Current approaches rely on self-declared capabilities and custom integration processes that create trust gaps and coordination friction limiting confident enterprise adoption. This paper presents AgentFacts, a universal metadata standard that enables systematic agent verification through cryptographically-signed capability declarations, multi-authority validation, and dynamic permission management. The specification introduces domain-specialized verification where different trusted authorities validate specific metadata aspects based on their expertise, eliminating single points of trust failure while enabling graduated confidence assessment. AgentFacts transforms agent procurement from custom integration projects into standardized workforce management, providing the transparency and governance infrastructure necessary for enterprise AI coordination at scale.

Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the preferences that they provide? And what is the ideal set of beliefs about an agent -- and resulting preferences -- for humans to have? We propose a new preference model that incorporates human beliefs and provide a normative theory that bounds the error on the final learned policy based on the \textit{mismatch} between the human's beliefs and an idealized set of beliefs. We then confirm via a human study that beliefs about agent capabilities do, in fact, significantly affect preferences and can be influenced through simple interventions. Additionally, we empirically show through synthetic experiments that it is often suboptimal for human preference labelers to assume agent optimality. Collectively, these results theoretically and empirically demonstrate how reducing the mismatch between human beliefs and agent capabilities can lead to more performant RLHF and point toward new best practices for RLHF practitioners.

-- With the rapid advancement of artificial intelligence, the proliferation of autonomous agents has introduced new challenges in interoperability, scalability, and coordination. The Internet of Agents (IoA) aims to interconnect heterogeneous agents through standardized communication protocols, enabling seamless collaboration and in telligent task execution. However, existing agent communication protocols such as MCP, A2A, and ANP remain fragmented and scenario - specific. To address this gap, we propose Agent Collaboration Protocols (ACPs), a comprehensive protocol suite for the IoA. A CPs include registration, discovery, interaction, and tooling protocols to support trustable access, capability orchestration, and workflow construction. We present the architecture, key technologies, and application workflows of ACPs, and demonstrate its effectiveness in a collaborative restaurant booking scenario. ACPs lay the foundation for building a secure, open, and scalable agent interconnecting infrastructure. In today's digital era, the rapid development of artificial intelligence has given rise to a new type of technical entity -- agents. As software or hardware entities endowed with autonomous capabilities for perception, decision - making, and execution, agents have increasingly become a focal point in technological advancement.

We introduce TimeSeriesGym, a scalable benchmarking framework for evaluating Artificial Intelligence (AI) agents on time series machine learning engineering challenges. Existing benchmarks lack scalability, focus narrowly on model building in well-defined settings, and evaluate only a limited set of research artifacts (e.g., CSV submission files). To make AI agent benchmarking more relevant to the practice of machine learning engineering, our framework scales along two critical dimensions. First, recognizing that effective ML engineering requires a range of diverse skills, TimeSeriesGym incorporates challenges from diverse sources spanning multiple domains and tasks. We design challenges to evaluate both isolated capabilities (including data handling, understanding research repositories, and code translation) and their combinations, and rather than addressing each challenge independently, we develop tools that support designing multiple challenges at scale. Second, we implement evaluation mechanisms for multiple research artifacts, including submission files, code, and models, using both precise numeric measures and more flexible LLM-based evaluation approaches. This dual strategy balances objective assessment with contextual judgment. Although our initial focus is on time series applications, our framework can be readily extended to other data modalities, broadly enhancing the comprehensiveness and practical utility of agentic AI evaluation. We open-source our benchmarking framework to facilitate future research on the ML engineering capabilities of AI agents.

Artificial Intelligence (AI) has evolved dramatically over the past decade, transitioning from specialized systems designed for narrow tasks to increasingly sophisticated architectures capable of autonomous operation across diverse domains. Among these advancements, AI agents represent a particularly significant development, embodying a paradigm shift in how intelligent systems interact with their environments, make decisions, and achieve complex goals. Unlike traditional AI systems that execute predefined algorithms within constraints, AI agents possess the capacity to autonomously perceive, reason, and act, often adapting their behavior based on environmental feedback and accumulated experience. The concept of an AI agent refers to a system or program that is capable of autonomously performing tasks on behalf of a user or another system by designing its workflow and utilizing available tools. These agents can encompass a wide range of functionalities beyond natural language processing, including decision making, problem solving, interacting with external environments, and executing actions. As Kapoor et al. (2024) note in their analysis of agent benchmarks, the development of AI agents represents an exciting new research direction with significant implications for real-world applications across numerous industries. The evolution of AI agents has been accelerated by recent breakthroughs in large language models (LLMs), which have provided a foundation for more sophisticated reasoning capabilities. Modern AI agents leverage these advanced language models as core components, augmenting them with specialized modules for memory, planning, tool use, and environmental interaction. This integration enables agents to perform complex tasks that would be challenging or impossible for traditional AI systems, from reconciling financial statements to providing step-by-step instructions for field technicians based on contextual understanding of product information.

Recent large language models (LLMs) have demonstrated significant advancements, particularly in their ability to serve as agents thereby surpassing their traditional role as chatbots. These agents can leverage their planning and tool utilization capabilities to address tasks specified at a high level. However, a standardized dataset to benchmark the agent capabilities of LLMs in medical applications is currently lacking, making the evaluation of LLMs on complex tasks in interactive healthcare environments challenging. To address this gap, we introduce MedAgentBench, a broad evaluation suite designed to assess the agent capabilities of large language models within medical records contexts. MedAgentBench encompasses 300 patient-specific clinically-derived tasks from 10 categories written by human physicians, realistic profiles of 100 patients with over 700,000 data elements, a FHIR-compliant interactive environment, and an accompanying codebase. The environment uses the standard APIs and communication infrastructure used in modern EMR systems, so it can be easily migrated into live EMR systems. MedAgentBench presents an unsaturated agent-oriented benchmark that current state-of-the-art LLMs exhibit some ability to succeed at. The best model (Claude 3.5 Sonnet v2) achieves a success rate of 69.67%. However, there is still substantial space for improvement which gives the community a next direction to optimize. Furthermore, there is significant variation in performance across task categories. MedAgentBench establishes this and is publicly available at https://github.com/stanfordmlgroup/MedAgentBench , offering a valuable framework for model developers to track progress and drive continuous improvements in the agent capabilities of large language models within the medical domain.

When using agent-task datasets to enhance agent capabilities for Large Language Models (LLMs), current methodologies often treat all tokens within a sample equally. However, we argue that tokens serving different roles - specifically, reasoning tokens versus boilerplate tokens (e.g., those governing output format) - differ significantly in importance and learning complexity, necessitating their disentanglement and distinct treatment. To address this, we propose a novel Shuffle-Aware Discriminator (SHAD) for adaptive token discrimination. SHAD classifies tokens by exploiting predictability differences observed after shuffling input-output combinations across samples: boilerplate tokens, due to their repetitive nature among samples, maintain predictability, whereas reasoning tokens do not. Using SHAD, we propose the Reasoning-highlighted Fine-Tuning (RFT) method, which adaptively emphasizes reasoning tokens during fine-tuning, yielding notable performance gains over common Supervised Fine-Tuning (SFT).

Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In this work, we introduce AgentBank, by far the largest trajectory tuning data collection featuring more than 50k diverse high-quality interaction trajectories which comprises 16 tasks covering five distinct agent skill dimensions. Leveraging a novel annotation pipeline, we are able to scale the annotated trajectories and generate a trajectory dataset with minimized difficulty bias. Furthermore, we fine-tune LLMs on AgentBank to get a series of agent models, Samoyed. Our comparative experiments demonstrate the effectiveness of scaling the interaction trajectory data to acquire generalized agent capabilities. Additional studies also reveal some key observations regarding trajectory tuning and agent skill generalization.