Related papers: HadAgent: Harness-Aware Decentralized Agentic AI S…
Data provenance and lineage are critical for ensuring integrity and reproducibility of information in research and application. This is particularly challenging for distributed scenarios, where data may be originating from decentralized…
AI agent inference is driving an inference heavy datacenter future and exposes bottlenecks beyond compute - especially memory capacity, memory bandwidth and high-speed interconnect. We introduce two metrics - Operational Intensity (OI) and…
The AI-based sensing and autonomous monitoring have become the main components of wildfire early detection, but current systems do not provide adaptive inter-agent coordination, structurally defined human control, and cryptographically…
Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale remains a fundamental challenge, particularly in decentralized…
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication…
The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…
Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…
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…
Proof-of-stake blockchain protocols have emerged as a compelling paradigm for organizing distributed ledger systems. In proof-of-stake (PoS), a subset of stakeholders participate in validating a growing ledger of transactions. For the…
Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inference engine (e.g., vLLM) and a tool orchestrator (e.g.,…
Endoscopic diagnosis is an iterative process in which clinicians progressively acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do not adequately support this process because fine-grained…
Agentic AI rivals human capabilities across a wide range of domains. Looking ahead, it is foreseeable that AI agents will autonomously handle complex workflows and interactions. Early prototypes of this paradigm are emerging, e.g., OpenClaw…
Blockchain is a decentralised, immutable ledger technology that has been widely adopted in many sectors for various applications such as cryptocurrencies, smart contracts and supply chain management. Distributed consensus is a fundamental…
A blockchain and smart contract enabled security mechanism for IoT applications has been reported recently for urban, financial, and network services. However, due to the power-intensive and a low-throughput consensus mechanism in existing…
Blockchain technologies originate from cryptocurrencies. Thus, most blockchain technologies assume an environment with a fast and stable network. However, in some blockchain-based systems, e.g., supply chain management (SCM) systems, some…
This paper presents a first empirical study of agentic AI as autonomous decision-makers in decentralized governance. Using more than 3K proposals from major protocols, we build an agentic AI voter that interprets proposal contexts,…
Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support short-horizon decision making under extreme volatility. However, existing trading systems…
In an age where sustainability is of paramount importance, the significance of both high-performance computing and intelligent algorithms cannot be understated. Yet, these domains often demand hefty computational power, translating to…
The Algorand blockchain is a secure and decentralized public ledger based on pure proof of stake rather than proof of work. At its core it is a novel consensus protocol with exactly one block certified in each round: that is, the protocol…
The decentralized trading market approach, where both autonomous agents and people can consume and produce services expanding own opportunities to reach goals, looks very promising as a part of the Fourth Industrial revolution. The key…