Training agents to operate under strict constraints during deployment, such as limited resource budgets or stringent safety requirements, presents significant challenges, especially when these constraints render the task complex. In this work, we propose a curriculum learning strategy that gradually tightens constraints during training, enabling the agent to incrementally master the deployment requirements. Inspired by self-paced learning techniques in unconstrained reinforcement learning (RL), our approach facilitates a smoother transition to challenging environments by initially training on simplified versions of the constraints and progressively introducing the full deployment conditions. We provide a theoretical analysis using an RL agent in a binary-tree Markov Decision Process (MDP) to demonstrate that our curriculum strategy can accelerate training relative to a baseline approach that imposes the trajectory constraints from the outset. Moreover, we empirically validate the effectiveness and generality of our method across both RL and large language model (LLM) agents in diverse settings, including a binary-tree MDP, a multi-task navigation domain, and a math reasoning task with two benchmarks. These results highlight the potential of curriculum design in enhancing the efficiency and performance of agents operating under complex trajectory constraints during deployment. Moreover, when applied to LLMs, our strategy enables compression of output chain-of-thought tokens, achieving a substantial inference speedup on consumer hardware, demonstrating its effectiveness for resource-constrained deployment.

The trajectory of AI development suggests that we will increasingly rely on agent-based systems composed of independently developed agents with different information, privileges, and tools. The success of these systems will critically depend on effective collaboration among these heterogeneous agents, even under partial observability. Despite intense interest, few empirical studies have evaluated such agent-agent collaboration at scale. We propose a collaborative maze-solving benchmark that (i) isolates collaborative capabilities, (ii) modulates problem complexity, (iii) enables scalable automated grading, and (iv) imposes no output-format constraints, preserving ecological plausibility. Using this framework, we evaluate 32 leading open- and closed-source models in solo, homogeneous, and heterogeneous pairings. Our results reveal a "collaboration gap": models that perform well solo often degrade substantially when required to collaborate. Collaboration can break down dramatically; for instance, small distilled models that solve mazes well alone may fail almost completely in certain pairings. We find that starting with the stronger agent often improves outcomes, motivating a "relay inference" approach where the stronger agent leads before handing off to the weaker one, closing much of the gap. Our findings argue for (1) collaboration-aware evaluation, (2) training strategies developed to enhance collaborative capabilities, and (3) interaction design that reliably elicits agents' latent skills, guidance that applies to AI-AI and human-AI collaboration.

Abstract--We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. T o simultaneously enhance communication efficiency and robustness against such adversaries, we propose a Byzantine-resilient Nesterov-Accelerated Federated Learning (Byrd-NAFL) algorithm. Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safeguarding convergence against gradient corruption. We establish a finite-time convergence guarantee for Byrd-NAFL under non-convex and smooth loss functions with relaxed assumption on the aggregated gradients. Extensive numerical experiments validate the effectiveness of Byrd-NAFL and demonstrate the superiority over existing benchmarks in terms of convergence speed, accuracy, and resilience to diverse Byzantine attack strategies. As a promising paradigm for privacy-preserving distributed learning, federated learning (FL) leverages the parallel computational capabilities of user terminals to learn from decentralized data with the orchestration of a central server. Since its inception [1], [2], FL has been proliferating across diverse application scenarios, e.g., healthcare [3], [4], mobile edge [5], [6], and autonomous driving [7], [8]. Despite the merits in preserving user privacy, vanilla FL paradigm is still facing two major challenges, namely, Byzantine resilience [9], [10] and communication efficiency [11]. To robustify the FL paradigm, Byzantine-resilient aggregation rules, e.g., Krum [10], the component-wise median (CwMed) [15], Bulyan [16], and geometric median (GeoMed) [17], are designed to enhance the trustworthiness and reliability of the FL paradigm. Another major challenge in FL lies in enhancing communication efficiency. Current communication-efficient FL algorithms can be broadly classified into three categories: (i) communication frequency reduction [18], [19], [20], [21], [22], [12], (ii) exchanged information compression [23], [24], [25], [6], and (iii) iteration reduction [20], [26], [27], [28].

Large language models (LLMs) are proliferating rapidly at the edge, delivering intelligent capabilities across diverse application scenarios. However, their practical deployment in collaborative scenarios confronts fundamental challenges: privacy vulnerabilities, communication overhead, and computational bottlenecks. To address these, we propose Federated Attention (FedAttn), which integrates the federated paradigm into the self-attention mechanism, creating a new distributed LLM inference framework that simultaneously achieves privacy protection, communication efficiency, and computational efficiency. FedAttn enables participants to perform local self-attention over their own token representations while periodically exchanging and aggregating Key-Value (KV) matrices across multiple Transformer blocks, collaboratively generating LLM responses without exposing private prompts. Further, we identify a structural duality between contextual representation refinement in FedAttn and parameter optimization in FL across private data, local computation, and global aggregation. This key insight provides a principled foundation for systematically porting federated optimization techniques to collaborative LLM inference. Building on this framework, we theoretically analyze how local self-attention computation within participants and heterogeneous token relevance among participants shape error propagation dynamics across Transformer blocks. Moreover, we characterize the fundamental trade-off between response quality and communication/computation efficiency, which is governed by the synchronization interval and the number of participants. Experimental results validate our theoretical analysis, and reveal significant optimization opportunities through sparse attention and adaptive KV aggregation, highlighting FedAttn's potential to deliver scalability and efficiency in real-world edge deployments.

The alignment of Large Language Models (LLMs) with human values is central to their safe deployment, yet current practice produces static, brittle, and costly-to-maintain models that fail to keep pace with evolving norms and policies. This misalignment, which we term the Alignment-Reality Gap, poses a growing challenge for reliable long-term use. Existing remedies are inadequate: large-scale re-annotation is economically prohibitive, and standard unlearning methods act as blunt instruments that erode utility rather than enable precise policy updates. We introduce TRACE (Triage and Re-align by Alignment Conflict Evaluation), a framework for principled unlearning that reconceives re-alignment as a pro-grammatic policy application problem. TRACE programmatically triages existing preference data against a new policy, identifies high-impact conflicts via a alignment impact score, and applies a hybrid optimization that cleanly inverts, discards, or preserves preferences while safeguarding model performance. Empirical results show that TRACE achieves robust re-alignment across diverse model families (Qwen2.5-7B, On both synthetic benchmarks and the PKU-SafeRLHF dataset under complex policy shift, TRACE enforces new principles without degrading general capabilities. Our work establishes a scalable, dynamic, and cost-effective paradigm for maintaining LLM alignment, providing a foundation for sustainable and responsible AI deployment. The advent of Large Language Models (LLMs) aligned with human values through Reinforcement Learning from Human Feedback (RLHF) represents a landmark achievement in artificial intelligence. This process transforms raw predictive models into safe and helpful agents, forming the bedrock of their widespread deployment. Y et, this bedrock is built on a profoundly brittle assumption: that human values are static.

Training and education in human-centered fields require authentic practice, yet realistic simulations of human behavior have remained limited. We present a multi-agent psychological simulation system that models internal cognitive-affective processes to generate believable human behaviors. In contrast to black-box neural models, this system is grounded in established psychological theories (e.g., self-efficacy, mindset, social constructivism) and explicitly simulates an ``inner parliament'' of agents corresponding to key psychological factors. These agents deliberate and interact to determine the system's output behavior, enabling unprecedented transparency and alignment with human psychology. We describe the system's architecture and theoretical foundations, illustrate its use in teacher training and research, and discuss how it embodies principles of social learning, cognitive apprenticeship, deliberate practice, and meta-cognition.

Quantum machine learning (QML) is a promising paradigm for tackling computational problems that challenge classical AI. Yet, the inherent probabilistic behavior of quantum mechanics, device noise in NISQ hardware, and hybrid quantum-classical execution pipelines introduce new risks that prevent reliable deployment of QML in real-world, safety-critical settings. This research offers a broad roadmap for Trustworthy Quantum Machine Learning (TQML), integrating three foundational pillars of reliability: (i) uncertainty quantification for calibrated and risk-aware decision making, (ii) adversarial robustness against classical and quantum-native threat models, and (iii) privacy preservation in distributed and delegated quantum learning scenarios. We formalize quantum-specific trust metrics grounded in quantum information theory, including a variance-based decomposition of predictive uncertainty, trace-distance-bounded robustness, and differential privacy for hybrid learning channels. To demonstrate feasibility on current NISQ devices, we validate a unified trust assessment pipeline on parameterized quantum classifiers, uncovering correlations between uncertainty and prediction risk, an asymmetry in attack vulnerability between classical and quantum state perturbations, and privacy-utility trade-offs driven by shot noise and quantum channel noise. This roadmap seeks to define trustworthiness as a first-class design objective for quantum AI.

Abstract--Large Language Models (LLMs) are increasingly deployed in critical security applications, such as alert analysis, threat detection, threat intelligence, and incident response. Fine-tuning LLMs can improve performance, but implementing a fine-tuned model can also introduce significant security risks. This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited dataset, can introduce significant bias, to the extent that a simple LLM-based alert investigator is completely bypassed when the prompt utilizes the introduced bias. Using fine-tuned Llama3.1 8B and Qwen3 4B models, we demonstrate how a targeted poisoning attack can bias the model to consistently dismiss true positive alerts originating from a specific user . Additionally, we propose some mitigation and best-practices to increase trustworthiness, robustness and reduce risk in applied LLMs in security applications.

We introduce Omega^2, a Large Language Model-driven framework for corporate credit scoring that combines structured financial data with advanced machine learning to improve predictive reliability and interpretability. Our study evaluates Omega^2 on a multi-agency dataset of 7,800 corporate credit ratings drawn from Moody's, Standard & Poor's, Fitch, and Egan-Jones, each containing detailed firm-level financial indicators such as leverage, profitability, and liquidity ratios. The system integrates CatBoost, LightGBM, and XGBoost models optimized through Bayesian search under temporal validation to ensure forward-looking and reproducible results. Omega^2 achieved a mean test AUC above 0.93 across agencies, confirming its ability to generalize across rating systems and maintain temporal consistency. These results show that combining language-based reasoning with quantitative learning creates a transparent and institution-grade foundation for reliable corporate credit-risk assessment.

The research explores error analysis in the performance of translating by Machine Translation from English into Romanian, and it focuses on lexical errors found in texts which include official information, provided by the World Health Organization (WHO), the Gavi Organization, by the patient information leaflet (the information about the active ingredients of the vaccines or the medication, the indications, the dosage instructions, the storage instructions, the side effects and warning, etc.). All of these texts are related to C ovid - 19 and have been translated by Google Translate, a multilingual Machine Translation that was created by Google. In the last decades, Google has actively work ed to develop a more accurate and fluent automatic translation system. This research, specifically focused on improving Google Translate, aims to enhance the overall quality of Machine Translation by achieving better lexical selection and by reducing errors. The investigation involves a comprehensive analysis of 230 texts that have been translated from English into Romanian.