The system demonstrated scalable, distributed threat detection, dynamic role classification, and responsive semantic analysis. Particularly, it achieved these capabilities without introducing processing bottlenecks or significant latency overhead. C. Conclusion This paper presented NetMoniAI, a hybrid agentic AI framework for real-time, distributed network monitoring and threat detection. By combining decentralized sensing at node level with centralized semantic analysis using GPT -O3, the system detects both localized and coordinated attacks with low latency and high accuracy. Evaluated across a local micro-testbed and NS-3 simulations, NetMoniAI demonstrated timely anomaly detection, accurate DDoS classification, and clear operator feedback through structured reports and an interactive dashboard. Its scalable, asynchronous architecture supports interpretable, layered responses without sacrificing performance. Future work will extend the framework with adaptive mitigation, multi-agent coordination, and SDN-based policy enforcement.

When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers threat modeling architecture in the system was used to expose, evaluate, and eliminate vulnerabilities of agentic AI. The prototype agent system was constructed and implemented, using Python, LangChain, and telemetry in WebSockets, and deployed with inference, memory, parameter tuning, and anomaly detection modules. Two practical threat cases were confirmed as follows: (i) resource denial of service by traffic replay denial-of-service, and (ii) memory poisoning by tampering with the historical log file maintained by the agent. These situations resulted in measurable levels of performance degradation, i.e. telemetry updates were delayed, and computational loads were increased, as a result of poor system adaptations. It was suggested to use a multilayered defense-in-depth approach with memory isolation, validation of planners and anomaly response systems in real-time. These findings verify that MAESTRO is viable in operational threat mapping, prospective risk scoring, and the basis of the resilient system design. The authors bring attention to the importance of the enforcement of memory integrity, paying attention to the adaptation logic monitoring, and cross-layer communication protection that guarantee the agentic AI reliability in adversarial settings.

Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To enable a more accurate assessment of AI agents in challenging exploratory environments, we introduce TextQuests, a benchmark based on the Infocom suite of interactive fiction games. These text-based adventures, which can take human players over 30 hours and require hundreds of precise actions to solve, serve as an effective proxy for evaluating AI agents on focused, stateful tasks. The benchmark is specifically designed to assess an LLM agent's capacity for self-contained problem-solving by precluding the use of external tools, thereby focusing on intrinsic long-context reasoning capabilities in an exploratory environment characterized by the need for trial-and-error learning and sustained problem-solving within a single interactive session. We release TextQuests at https://textquests.ai.

This paper introduces a novel multi-agent ski-rental problem that generalizes the classical ski-rental dilemma to a group setting where agents incur individual and shared costs. In our model, each agent can either rent at a fixed daily cost, or purchase a pass at an individual cost, with an additional third option of a discounted group pass available to all. We consider scenarios in which agents' active days differ, leading to dynamic states as agents drop out of the decision process. To address this problem from different perspectives, we define three distinct competitive ratios: overall, state-dependent, and individual rational. For each objective, we design and analyze optimal deterministic and randomized policies. Our deterministic policies employ state-aware threshold functions that adapt to the dynamic states, while our randomized policies sample and resample thresholds from tailored state-aware distributions. The analysis reveals that symmetric policies, in which all agents use the same threshold, outperform asymmetric ones. Our results provide competitive ratio upper and lower bounds and extend classical ski-rental insights to multi-agent settings, highlighting both theoretical and practical implications for group decision-making under uncertainty.

Matching markets are often organized in a multi-stage and decentralized manner. Moreover, participants in real-world matching markets often have uncertain preferences.

We study voting rules for participatory budgeting, where a group of voters collectively decides which projects should be funded using a common budget.

A, B to denote allocations that are exclusively integral and R for randomized allocations. On a high level, the PS-Lottery algorithm uses Birkhoff's We begin by proving a lemma that highlights a connection between not obvious manipulability and randomized mechanisms that output ex-ante proportional allocations. Lemma 5. Inequality (1) (the worst-case guarantee) is satisfied for every randomized mechanism Note that multiple randomized allocations may have the same expected fractional allocation. Recall that, Birkhoff's algorithm, given a square bistochastic matrix, decomposes it into a convex combination (or a lottery) over permutation matrices. Using Lemma 5 we can prove the following theorem.

It is well-understood that, in the absence of monetary transfers, fairness, efficiency and truthfulness cannot be reconciled, in a very strong sense.

We study envy-free policy teaching.