Recent advances in Embodied AI have enabled agents to perform increasingly complex tasks and adapt to diverse environments. However, deploying such agents in realistic human-centered scenarios, such as domestic households, remains challenging, particularly due to the difficulty of modeling individual human preferences and behaviors. In this work, we introduce PersONAL (PERSonalized Object Navigation And Localization, a comprehensive benchmark designed to study personalization in Embodied AI. Agents must identify, retrieve, and navigate to objects associated with specific users, responding to natural-language queries such as "find Lily's backpack". PersONAL comprises over 2,000 high-quality episodes across 30+ photorealistic homes from the HM3D dataset. Each episode includes a natural-language scene description with explicit associations between objects and their owners, requiring agents to reason over user-specific semantics. The benchmark supports two evaluation modes: (1) active navigation in unseen environments, and (2) object grounding in previously mapped scenes. Experiments with state-of-the-art baselines reveal a substantial gap to human performance, highlighting the need for embodied agents capable of perceiving, reasoning, and memorizing over personalized information; paving the way towards real-world assistive robot.

The rapid advancement of generative AI has democratized access to powerful tools such as Text-to-Image models. However, to generate high-quality images, users must still craft detailed prompts specifying scene, style, and context-often through multiple rounds of refinement. We propose PromptSculptor, a novel multi-agent framework that automates this iterative prompt optimization process. Our system decomposes the task into four specialized agents that work collaboratively to transform a short, vague user prompt into a comprehensive, refined prompt. By leveraging Chain-of-Thought reasoning, our framework effectively infers hidden context and enriches scene and background details. To iteratively refine the prompt, a self-evaluation agent aligns the modified prompt with the original input, while a feedback-tuning agent incorporates user feedback for further refinement. Experimental results demonstrate that PromptSculptor significantly enhances output quality and reduces the number of iterations needed for user satisfaction. Moreover, its model-agnostic design allows seamless integration with various T2I models, paving the way for industrial applications.

Continuous-time Conflict Based-Search (CCBS) has long been viewed as the standard optimal baseline for multi-agent path finding in continuous time (MAPFR), yet recent critiques show that the theoretically described CCBS can fail to terminate on solvable MAPFR problems while the publicly available reference implementation can return sub-optimal solutions. This work presents an analytical framework that yields simple and sufficient conditions under which any CCBS-style algorithm is both sound and solution complete. Investigating the reference CCBS implementation reveals that it violates our sufficient conditions for soundness, with counterexamples demonstrating sub-optimality. Leveraging the framework, we introduce a branching rule ($δ$-BR) and prove it restores soundness and termination guarantees. Consequently, the resulting CCBS variant is both sound and solution complete. To our knowledge, this is the first MAPFR solver matching the guarantees of the discrete-time CBS. On a constructed example, CCBS with $δ$-BR improves sum-of-costs from 10.707 to 9.000 ($\approx$ 16% lower) compared to the reference CCBS implementation. Across benchmarks, the reference CCBS implementation is generally able to find solutions faster than CCBS with $δ$-BR due to its more aggressive pruning. However, this comes at the cost of occasional sub-optimality and potential non-termination when all solutions are pruned, whereas $δ$-BR preserves optimality and guarantees termination by design. Because $δ$-BR largely only affects the branching step, it can be adopted as a drop-in replacement in existing codebases. Beyond CCBS, the analytical framework and termination criterion provide a systematic way to evaluate other CCBS-like MAPFR solvers and future extensions, thereby offering tools for rigorous analysis of next-generation MAPFR algorithms.

Graphical User Interface (GUI) agents powered by Large Vision-Language Models (LVLMs) have emerged as a revolutionary approach to automating human-machine interactions, capable of autonomously operating personal devices (e.g., mobile phones) or applications within the device to perform complex real-world tasks in a human-like manner. However, their close integration with personal devices raises significant security concerns, with many threats, including backdoor attacks, remaining largely unexplored. This work reveals that the visual grounding of GUI agent-mapping textual plans to GUI elements-can introduce vulnerabilities, enabling new types of backdoor attacks. With backdoor attack targeting visual grounding, the agent's behavior can be compromised even when given correct task-solving plans. To validate this vulnerability, we propose VisualTrap, a method that can hijack the grounding by misleading the agent to locate textual plans to trigger locations instead of the intended targets. VisualTrap uses the common method of injecting poisoned data for attacks, and does so during the pre-training of visual grounding to ensure practical feasibility of attacking. Empirical results show that VisualTrap can effectively hijack visual grounding with as little as 5% poisoned data and highly stealthy visual triggers (invisible to the human eye); and the attack can be generalized to downstream tasks, even after clean fine-tuning. Moreover, the injected trigger can remain effective across different GUI environments, e.g., being trained on mobile/web and generalizing to desktop environments. These findings underscore the urgent need for further research on backdoor attack risks in GUI agents.

Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have resource or failure constraints where action sequences may be forcibly terminated once resources are exhausted, agents face implicit trade-offs that reshape their utility-driven (rational) behaviour. Additionally, since these agents are typically commissioned by a human principal to act on their behalf, asymmetries in constraint exposure can give rise to previously unanticipated misalignment between human objectives and agent incentives. We formalise this setting through a survival bandit framework, provide theoretical and empirical results that quantify the impact of survival-driven preference shifts, identify conditions under which misalignment emerges and propose mechanisms to mitigate the emergence of risk-seeking or risk-averse behaviours. As a result, this work aims to increase understanding and interpretability of emergent behaviours of AI agents operating under such survival pressure, and offer guidelines for safely deploying such AI systems in critical resource-limited environments.

We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable profiles that make agent capabilities searchable through semantic embeddings, enabling agents to advertise their capabilities, cost, and limitations. Our aarchitecturecombines three key innovations: (1) semantic routing that matches tasks to agents over sharded HNSW indices while enforcing operational constraints through cost-biased optimization, (2) dynamic task decomposition where compatible agents collaboratively break down complex tasks into DAGs of subtasks through consensus-based merging, and (3) smart clustering that groups agents working on similar subtasks into collaborative channels for k-round refinement before synthesis. Built on top of MQTT,s publish-subscribe semantics for scalable message passing, FoA achieves sub-linear complexity through hierarchical capability matching and efficient index maintenance. Evaluation on HealthBench shows 13x improvements over single-model baselines, with clustering-enhanced laboration particularly effective for complex reasoning tasks requiring multiple perspectives. The system scales horizontally while maintaining consistent performance, demonstrating that semantic orchestration with structured collaboration can unlock the collective intelligence of heterogeneous federations of AI agents.

Swarm intelligence emerges from decentralised interactions among simple agents, enabling collective problem-solving. This study establishes a theoretical equivalence between pheromone-mediated aggregation in \celeg\ and reinforcement learning (RL), demonstrating how stigmergic signals function as distributed reward mechanisms. We model engineered nematode swarms performing foraging tasks, showing that pheromone dynamics mathematically mirror cross-learning updates, a fundamental RL algorithm. Experimental validation with data from literature confirms that our model accurately replicates empirical \celeg\ foraging patterns under static conditions. In dynamic environments, persistent pheromone trails create positive feedback loops that hinder adaptation by locking swarms into obsolete choices. Through computational experiments in multi-armed bandit scenarios, we reveal that introducing a minority of exploratory agents insensitive to pheromones restores collective plasticity, enabling rapid task switching. This behavioural heterogeneity balances exploration-exploitation trade-offs, implementing swarm-level extinction of outdated strategies. Our results demonstrate that stigmergic systems inherently encode distributed RL processes, where environmental signals act as external memory for collective credit assignment. By bridging synthetic biology with swarm robotics, this work advances programmable living systems capable of resilient decision-making in volatile environments.

Abstract--This study proposes a hybrid safety verification framework for closed-loop multi-agent systems under bounded stochastic disturbances. The proposed approach augments control barrier functions with a novel ψ-weighted formulation that encodes directional control alignment between agents into the safety constraints. Deterministic admissibility is combined with empirical validation via Monte Carlo rollouts, and a PAC-style guarantee is derived based on margin-aware safety violations to provide a probabilistic safety certificate. The results from the experiments conducted under different bounded stochastic disturbances validate the feasibility of the proposed approach. Safety within multi-agent systems is essential for real-world applications such as autonomous driving [1], [2] and robotic swarm deployments in agriculture [3], [4], manufacturing [5], [6], and search and rescue operations [7], where agents must navigate safely through their environment.

Human drivers focus only on a handful of agents at any one time. On the other hand, autonomous driving systems process complex scenes with numerous agents, regardless of whether they are pedestrians on a crosswalk or vehicles parked on the side of the road. While attention mechanisms offer an implicit way to reduce the input to the elements that affect decisions, existing attention mechanisms for capturing agent interactions are quadratic, and generally computationally expensive. We propose RDAR, a strategy to learn per-agent relevance -- how much each agent influences the behavior of the controlled vehicle -- by identifying which agents can be excluded from the input to a pre-trained behavior model. We formulate the masking procedure as a Markov Decision Process where the action consists of a binary mask indicating agent selection. We evaluate RDAR on a large-scale driving dataset, and demonstrate its ability to learn an accurate numerical measure of relevance by achieving comparable driving performance, in terms of overall progress, safety and performance, while processing significantly fewer agents compared to a state of the art behavior model.

The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs, or encounter unrecoverable failures, leading to user frustration and a breakdown of trust. This report proposes a novel architectural pattern to address these issues: the integration of a secondary, "metacognitive" layer that actively monitors the primary LCNC agent. Inspired by human introspection, this layer is designed to predict impending task failures based on a defined set of triggers, such as excessive latency or repetitive actions. Upon predicting a failure, the metacognitive agent proactively initiates a human handoff, providing the user with a clear summary of the agent's "thought process" and a detailed explanation of why it could not proceed. An empirical analysis of a prototype system demonstrates that this approach significantly increases the overall task success rate. However, this performance gain comes with a notable increase in computational overhead. The findings reframe human handoffs not as an admission of defeat but as a core design feature that enhances system resilience, improves user experience, and builds trust by providing transparency into the agent's internal state. The report discusses the practical and ethical implications of this approach and identifies key directions for future research.