Related papers: From Risk to Rescue: An Agentic Survival Analysis …
The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…
As software systems grow in complexity, security vulnerabilities have become increasingly prevalent, posing serious risks and economic costs. Although automated detection tools such as fuzzers have advanced considerably, effective…
In this paper, our objective is to develop a multi-agent financial system that incorporates simulated trading, a technique extensively utilized by financial professionals. While current LLM-based agent models demonstrate competitive…
Decentralized Finance (DeFi) is emerging as a peer-to-peer financial ecosystem, enabling participants to trade products on a permissionless blockchain. Built on blockchain and smart contracts, the DeFi ecosystem has experienced explosive…
Motivated by the recent interest in formal methods-based control of multi-agent systems, we adopt a bottom-up approach. Each agent is subject to a local signal temporal logic task that may depend on other agents behavior. These dependencies…
The Internet of Electric Vehicles (IoEV) envisions a tightly coupled ecosystem of electric vehicles (EVs), charging infrastructure, and grid services, yet it remains vulnerable to cyberattacks, unreliable battery-state predictions, and…
This paper addresses the problem of navigation control of a general class of uncertain nonlinear multi-agent systems in a bounded workspace of $\mathbb{R}^n$ with static obstacles. In particular, we propose a decentralized control protocol…
Assessing the stability of economic systems is a fundamental research focus in economics, that has become increasingly interdisciplinary in the currently troubled economic situation. In particular, much attention has been devoted to the…
The Internet of Value (IoV) is a heterogeneous, partially-trusted network in which the dominant marginal risk is composite (route, sentiment, liquidity, and the policy a system is willing to commit to) rather than a property of any single…
A novel procedure is presented for the objective comparison and evaluation of a bank's decision rules in optimising the timing of loan recovery. This procedure is based on finding a delinquency threshold at which the financial loss of a…
Although Federated Learning (FL) promises privacy and distributed collaboration, its effectiveness in real-world scenarios is often hampered by the stochastic heterogeneity of clients and unpredictable system dynamics. Existing static…
This paper addresses the critical challenge of mesa-optimization in AI safety by providing a formal definition of agency and a framework for its analysis. Agency is conceptualized as a Continuous Representation of accumulated experience…
Safely navigating through an urban environment without violating any traffic rules is a crucial performance target for reliable autonomous driving. In this paper, we present a Reinforcement Learning (RL) based methodology to DEtect and FIX…
Agentic AI, with goal-directed, proactive, and autonomous decision-making capabilities, offers a compelling opportunity to address movement-related risks in human activity, including the persistent hazard of falls among elderly populations.…
In many real-world multi-agent cooperative tasks, due to high cost and risk, agents cannot continuously interact with the environment and collect experiences during learning, but have to learn from offline datasets. However, the transition…
We propose Dr.Aid, a logic-based AI framework for automated compliance checking of data governance rules over data-flow graphs. The rules are modelled using a formal language based on situation calculus and are suitable for decentralized…
Modern clinical decision support systems can concurrently serve multiple, independent medical imaging institutions, but their predictive performance may degrade across sites due to variations in patient populations, imaging hardware, and…
This paper proposes a scalable decentralized safety filter for multi-agent systems based on high-order control barrier functions (HOCBFs) and auction-based responsibility allocation. While decentralized HOCBF formulations ensure pairwise…
While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. Current solutions often resort to rigid structural engineering or expensive fine-tuning,…
Operating Elasticsearch clusters at scale demands continuous human expertise spanning the full lifecycle -- from initial deployment through performance tuning, monitoring, failure prediction, and incident recovery. We present the ES…