The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional cybersecurity paradigms are ill-equipped to address. This paper introduces the Aegis Protocol, a layered security framework designed to provide strong security guarantees for open agentic ecosystems. The protocol integrates three technological pillars: (1) non-spoofable agent identity via W3C Decentralized Identifiers (DIDs); (2) communication integrity via NIST-standardized post-quantum cryptography (PQC); and (3) verifiable, privacy-preserving policy compliance using the Halo2 zero-knowledge proof (ZKP) system. We formalize an adversary model extending Dolev-Yao for agentic threats and validate the protocol against the STRIDE framework. Our quantitative evaluation used a discrete-event simulation, calibrated against cryptographic benchmarks, to model 1,000 agents. The simulation showed a 0 percent success rate across 20,000 attack trials. For policy verification, analysis of the simulation logs reported a median proof-generation latency of 2.79 seconds, establishing a performance baseline for this class of security. While the evaluation is simulation-based and early-stage, it offers a reproducible baseline for future empirical studies and positions Aegis as a foundation for safe, scalable autonomous AI.

As AI systems evolve into distributed ecosystems with autonomous execution, asynchronous reasoning, and multi-agent coordination, the absence of scalable, decoupled governance poses a structural risk. Existing oversight mechanisms are reactive, brittle, and embedded within agent architectures, making them non-auditable and hard to generalize across heterogeneous deployments. We introduce Governance-as-a-Service (GaaS): a modular, policy-driven enforcement layer that regulates agent outputs at runtime without altering model internals or requiring agent cooperation. GaaS employs declarative rules and a Trust Factor mechanism that scores agents based on compliance and severity-weighted violations. It enables coercive, normative, and adaptive interventions, supporting graduated enforcement and dynamic trust modulation. To evaluate GaaS, we conduct three simulation regimes with open-source models (LLaMA3, Qwen3, DeepSeek-R1) across content generation and financial decision-making. In the baseline, agents act without governance; in the second, GaaS enforces policies; in the third, adversarial agents probe robustness. All actions are intercepted, evaluated, and logged for analysis. Results show that GaaS reliably blocks or redirects high-risk behaviors while preserving throughput. Trust scores track rule adherence, isolating and penalizing untrustworthy components in multi-agent systems. By positioning governance as a runtime service akin to compute or storage, GaaS establishes infrastructure-level alignment for interoperable agent ecosystems. It does not teach agents ethics; it enforces them.

Recent multi-agent frameworks built upon large language models (LLMs) have demonstrated remarkable capabilities in complex task planning. However, in real-world enterprise environments, business workflows are typically composed through modularization and reuse of numerous subprocesses, resulting in intricate workflows characterized by lengthy and deeply nested execution paths. Such complexity poses significant challenges for LLM-driven orchestration, as extended reasoning chains and state-space explosions severely impact planning effectiveness and the proper sequencing of tool invocations. Therefore, developing an orchestration method with controllable structures capable of handling multi-layer nesting becomes a critical issue. To address this, we propose a novel structure-driven orchestration framework-- Self-Organizing Agent Network (SOAN) . SOAN incrementally builds a formalized agent network by identifying and encapsulating structural units as independent agents, enhancing modularity and clarity in orchestration. Extensive evaluations were performed using multiple benchmarks as well as a real-world enterprise workflow dataset. Experimental results demonstrate that SOAN significantly outperforms state-of-the-art methods in terms of adaptability, fault tolerance, and execution efficiency.

This paper introduces a two-timescale hierarchical decentralized control architecture for Cyber-Physical Systems (CPS). The system consists of a global controller (GC), and N local controllers (LCs). The GC operates at a slower timescale, imposing budget constraints on the actions of LCs, which function at a faster timescale. Applications can be found in energy grid planning, wildfire management, and other decentralized resource allocation problems. We propose and analyze two optimization frameworks for this setting: COpt and FOpt. In COpt, both GC and LCs together optimize infinite-horizon discounted rewards, while in FOpt the LCs optimize finite-horizon episodic rewards, and the GC optimizes infinite-horizon rewards. Although both frameworks share identical reward functions, their differing horizons can lead to different optimal policies. In particular, FOpt grants greater autonomy to LCs by allowing their policies to be determined only by local objectives, unlike COpt. To our knowledge, these frameworks have not been studied in the literature. We establish the formulations, prove the existence of optimal policies, and prove the convergence of their value iteration algorithms. We further show that COpt always achieves a higher value function than FOpt and derive explicit bounds on their difference. Finally, we establish a set of sufficient structural conditions under which the two frameworks become equivalent.

Yesterday, Anthropic unveiled Claude for Chrome, a brand-new browser extension that acts as an AI agent. In short, the extension allows you to chat with Claude in a side panel while using Chrome, and Claude will perform actions on your behalf based on what you want it to do. The Claude AI chatbot will keep track of your open tabs, and in doing so will analyze and understand the context of any prompt you submit and any action you ask it to perform, like completing an online order. In the video below, you can see how it's supposed to work: To begin with, only customers with an active Max subscription will have access to Claude for Chrome, and even then only 1,000 users can participate in the pilot program. As Anthropic gains confidence in Claude for Chrome, more users will be invited to participate.

Google has fixed a critical vulnerability in Chrome versions 139.0.7258.154/155 According to Google, the vulnerability has not yet been exploited for attacks in the wild. The manufacturers of other Chromium-based browsers are expected to follow suit in the coming days. In the Chrome Releases blog post, Krishna Govind presents the eliminated vulnerability (CVE-2025-9478), which is treated as if it were discovered by external security researchers, but Google Big Sleep is named as the discoverer of the vulnerability. This is an "AI" tool based on Gemini for detecting security vulnerabilities and it's designed to detect vulnerabilities on its own without human assistance.

With the recent rapid advancement of Agentic Intelligence, agentic tool use in LLMs has become increasingly important. During multi-turn interactions between agents and users, the dynamic, uncertain, and stochastic nature of user demands poses significant challenges to the agent's tool invocation capabilities. Agents are no longer expected to simply call tools to deliver a result; rather, they must iteratively refine their understanding of user needs through communication while simultaneously invoking tools to resolve user queries. Existing reinforcement learning (RL) approaches for tool use lack the integration of genuinely dynamic users during the RL training process. To bridge this gap, we introduce MUA-RL (Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use), a novel reinforcement learning framework that, for the first time in the field of agentic tool use, integrates LLM-simulated users into the reinforcement learning loop. MUA-RL aims to enable autonomous learning of models to communicate with users efficiently and use various tools to solve practical problems in dynamic multi-turn interactions. Evaluations are done on several multi-turn tool-using benchmarks (see Figure 1). Specifically, MUA-RL-32B achieves 67.3 on TAU2 Retail, 45.4 on TAU2 Airline, 28.3 on TAU2 Telecom, 28.4 on BFCL-V3 Multi Turn, and 82.5 on ACEBench Agent -- outperforming or matching the performance of larger open-source models such as DeepSeek-V3-0324 and Qwen3-235B-A22B in non-thinking settings.

Guard patrol behavior is central to the immersion and strategic depth of stealth games, while most existing systems rely on hand-crafted routes or specialized logic that struggle to balance coverage efficiency and responsive pursuit with believable naturalness. We propose a generic, fully explainable, training-free framework that integrates global knowledge and local information via Composite Potential Fields, combining three interpretable maps-Information, Confidence, and Connectivity-into a single kernel-filtered decision criterion. Our parametric, designer-driven approach requires only a handful of decay and weight parameters-no retraining-to smoothly adapt across both occupancy-grid and NavMesh-partition abstractions. We evaluate on five representative game maps, two player-control policies, and five guard modes, confirming that our method outperforms classical baseline methods in both capture efficiency and patrol naturalness. Finally, we show how common stealth mechanics-distractions and environmental elements-integrate naturally into our framework as sub modules, enabling rapid prototyping of rich, dynamic, and responsive guard behaviors.

We introduce the Concurrent Modular Agent (CMA), a framework that orchestrates multiple Large-Language-Model (LLM)-based modules that operate fully asynchronously yet maintain a coherent and fault-tolerant behavioral loop. This framework addresses long-standing difficulties in agent architectures by letting intention emerge from language-mediated interactions among autonomous processes. This approach enables flexible, adaptive, and context-dependent behavior through the combination of concurrently executed modules that offload reasoning to an LLM, inter-module communication, and a single shared global state.We consider this approach to be a practical realization of Minsky's Society of Mind theory. We demonstrate the viability of our system through two practical use-case studies. The emergent properties observed in our system suggest that complex cognitive phenomena like self-awareness may indeed arise from the organized interaction of simpler processes, supporting Minsky-Society of Mind concept and opening new avenues for artificial intelligence research. The source code for our work is available at: https://github.com/AlternativeMachine/concurrent-modular-agent.

--Incorporating ethics into the requirement elicitation process is essential for creating ethically aligned systems. Although eliciting manual ethics requirements is effective, it requires diverse input from multiple stakeholders, which can be challenging due to time and resource constraints. Moreover, it is often given a low priority in the requirements elicitation process. This study proposes a framework for generating ethics requirements drafts by introducing an ethics advocate agent in a multi-agent LLM setting. This agent critiques and provides input on ethical issues based on the system description. The proposed framework is evaluated through two case studies from different contexts, demonstrating that it captures the majority of ethics requirements identified by researchers during 30-minute interviews and introduces several additional relevant requirements. However, it also highlights reliability issues in generating ethics requirements, emphasizing the need for human feedback in this sensitive domain. We believe this work can facilitate the broader adoption of ethics in the requirements engineering process, ultimately leading to more ethically aligned products. Artificial intelligence (AI) has gained widespread adoption across various domains, including healthcare, finance, education, and marketing.