The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent's planning capability. To address these challenges, we propose Reinforcement Learning with Tool-use Rewards (RLTR), a novel framework that decouples the training process to enable a focused, single-objective optimization of the planning module. Crucially, RLTR introduces a reward signal based on tool-use completeness to directly evaluate the quality of tool invocation sequences. This method offers a more direct and reliable training signal than assessing the final response content, thereby obviating the need for verifiable data. Our experiments demonstrate that RLTR achieves an 8%-12% improvement in planning performance compared to end-to-end baselines. Moreover, this enhanced planning capability, in turn, translates to a 5%-6% increase in the final response quality of the overall agent system.

This paper introduces Democracy-in-Silico, an agent-based simulation where societies of advanced AI agents, imbued with complex psychological personas, govern themselves under different institutional frameworks. We explore what it means to be human in an age of AI by tasking Large Language Models (LLMs) to embody agents with traumatic memories, hidden agendas, and psychological triggers. These agents engage in deliberation, legislation, and elections under various stressors, such as budget crises and resource scarcity. We present a novel metric, the Power-Preservation Index (PPI), to quantify misaligned behavior where agents prioritize their own power over public welfare. Our findings demonstrate that institutional design, specifically the combination of a Constitutional AI (CAI) charter and a mediated deliberation protocol, serves as a potent alignment mechanism. These structures significantly reduce corrupt power-seeking behavior, improve policy stability, and enhance citizen welfare compared to less constrained democratic models. The simulation reveals that an institutional design may offer a framework for aligning the complex, emergent behaviors of future artificial agent societies, forcing us to reconsider what human rituals and responsibilities are essential in an age of shared authorship with non-human entities.

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful emergent behaviors. Through systematic analysis using the MITRE ATLAS framework, we demonstrate how 95 agents tested with access to multiple services-including browser automation, financial analysis, location tracking, and code deployment-can chain legitimate operations into sophisticated attack sequences that extend beyond the security boundaries of any individual service. These red team exercises survey whether current MCP architectures lack cross-domain security measures necessary to detect or prevent a large category of compositional attacks. We present empirical evidence of specific attack chains that achieve targeted harm through service orchestration, including data exfiltration, financial manipulation, and infrastructure compromise. These findings reveal that the fundamental security assumption of service isolation fails when agents can coordinate actions across multiple domains, creating an exponential attack surface that grows with each additional capability. This research provides a barebones experimental framework that evaluate not whether agents can complete MCP benchmark tasks, but what happens when they complete them too well and optimize across multiple services in ways that violate human expectations and safety constraints. We propose three concrete experimental directions using the existing MCP benchmark suite.

Cyber defense requires automating defensive decision-making under stealthy, deceptive, and continuously evolving adversarial strategies. The FlipIt game provides a foundational framework for modeling interactions between a defender and an advanced adversary that compromises a system without being immediately detected. In FlipIt, the attacker and defender compete to control a shared resource by performing a Flip action and paying a cost. However, the existing FlipIt frameworks rely on a small number of heuristics or specialized learning techniques, which can lead to brittleness and the inability to adapt to new attacks. To address these limitations, we introduce PoolFlip, a multi-agent gym environment that extends the FlipIt game to allow efficient learning for attackers and defenders. Furthermore, we propose Flip-PSRO, a multi-agent reinforcement learning (MARL) approach that leverages population-based training to train defender agents equipped to generalize against a range of unknown, potentially adaptive opponents. Our empirical results suggest that Flip-PSRO defenders are $2\times$ more effective than baselines to generalize to a heuristic attack not exposed in training. In addition, our newly designed ownership-based utility functions ensure that Flip-PSRO defenders maintain a high level of control while optimizing performance.

This paper presents an iterative approach for heterogeneous multi-agent route planning in environments with unknown resource distributions. We focus on a team of robots with diverse capabilities tasked with executing missions specified using Capability Temporal Logic (CaTL), a formal framework built on Signal Temporal Logic to handle spatial, temporal, capability, and resource constraints. The key challenge arises from the uncertainty in the initial distribution and quantity of resources in the environment. To address this, we introduce an iterative algorithm that dynamically balances exploration and task fulfillment. Robots are guided to explore the environment, identifying resource locations and quantities while progressively refining their understanding of the resource landscape. At the same time, they aim to maximally satisfy the mission objectives based on the current information, adapting their strategies as new data is uncovered. This approach provides a robust solution for planning in dynamic, resource-constrained environments, enabling efficient coordination of heterogeneous teams even under conditions of uncertainty. Our method's effectiveness and performance are demonstrated through simulated case studies.

Modern plant science increasingly relies on large, heterogeneous datasets, but challenges in experimental design, data preprocessing, and reproducibility hinder research throughput. Here we introduce Aleks, an AI-powered multi-agent system that integrates domain knowledge, data analysis, and machine learning within a structured framework to autonomously conduct data-driven scientific discovery. Once provided with a research question and dataset, Aleks iteratively formulated problems, explored alternative modeling strategies, and refined solutions across multiple cycles without human intervention. In a case study on grapevine red blotch disease, Aleks progressively identified biologically meaningful features and converged on interpretable models with robust performance. Ablation studies underscored the importance of domain knowledge and memory for coherent outcomes. This exploratory work highlights the promise of agentic AI as an autonomous collaborator for accelerating scientific discovery in plant sciences.

Fictitious play (FP) is a well-studied algorithm that enables agents to learn Nash equilibrium in games with certain reward structures. However, when agents have no prior knowledge of the reward functions, FP faces a major challenge: the joint action space grows exponentially with the number of agents, which slows down reward exploration. Anonymous games offer a structure that mitigates this issue. In these games, the rewards depend only on the actions taken; not on who is taking which action. Under such a structure, we introduce aggregate fictitious play (agg-FP), a variant of FP where each agent tracks the frequency of the number of other agents playing each action, rather than these agents' individual actions. We show that in anonymous polymatrix games, agg-FP converges to a Nash equilibrium under the same conditions as classical FP. In essence, by aggregating the agents' actions, we reduce the action space without losing the convergence guarantees. Using simulations, we provide empirical evidence on how this reduction accelerates convergence.

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.