Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce Symphony, a decentralized multi-agent system which enables lightweight LLMs on consumer-grade GPUs to coordinate. Symphony introduces three key mechanisms: (1) a decentralized ledger that records capabilities, (2) a Beacon-selection protocol for dynamic task allocation, and (3) weighted result voting based on CoTs. This design forms a privacy-saving, scalable, and fault-tolerant orchestration with low overhead. Empirically, Symphony outperforms existing baselines on reasoning benchmarks, achieving substantial accuracy gains and demonstrating robustness across models of varying capacities.

The rapid advancement of large vision language models (L VLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however, remain limited by structural constraints. Although multi-agent systems naturally decouple different competencies, recent progress in multi-agent reinforcement learning (MARL) has often been hindered by inefficiency and remains incompatible with current L VLM architectures. To address these challenges, we introduce SWIRL, a staged workflow for interleaved reinforcement learning designed for multi-agent systems. SWIRL reformulates MARL into a sequence of single-agent reinforcement learning tasks, updating one agent at a time while keeping the others fixed. This formulation enables stable training and promotes efficient coordination across agents. Theoretically, we provide a stepwise safety bound, a cross-round monotonic improvement theorem, and convergence guarantees on return, ensuring robust and principled optimization. In application to mobile GUI control, SWIRL instantiates a Navigator that converts language and screen context into structured plans, and an Interactor that grounds these plans into executable atomic actions. Extensive experiments demonstrate superior performance on both high-level and low-level GUI benchmarks. Beyond GUI tasks, SWIRL also demonstrates strong capability in multi-agent mathematical reasoning, underscoring its potential as a general framework for developing efficient and robust multi-agent systems.

Cataract surgery remains one of the most widely performed and effective procedures for vision restoration. Effective surgical planning requires integrating diverse clinical examinations for patient assessment, intraocular lens (IOL) selection, and risk evaluation. Large language models (LLMs) have shown promise in supporting clinical decision-making. However, existing LLMs often lack the domain-specific expertise to interpret heterogeneous ophthalmic data and provide actionable surgical plans. To enhance the model's ability to interpret heterogeneous ophthalmic reports, we propose a knowledge-driven Multi-Agent System (MAS), where each agent simulates the reasoning process of specialist ophthalmologists, converting raw clinical inputs into structured, actionable summaries in both training and deployment stages. Building on MAS, we introduce CataractSurg-80K, the first large-scale benchmark for cataract surgery planning that incorporates structured clinical reasoning. Each case is annotated with diagnostic questions, expert reasoning chains, and structured surgical recommendations. We further introduce Qwen-CSP, a domain-specialized model built on Qwen-4B, fine-tuned through a multi-stage process tailored for surgical planning. Comprehensive experiments show that Qwen-CSP outperforms strong general-purpose LLMs across multiple metrics. Our work delivers a high-quality dataset, a rigorous benchmark, and a domain-adapted LLM to facilitate future research in medical AI reasoning and decision support.

Optimizing modern production plants using the job-shop principle is a known hard problem. For very large plants, like semiconductor fabs, the problem becomes unsolvable on a plant-wide scale in a reasonable amount of time using classical linear optimization. An alternative approach is the use of swarm intelligence algorithms. These have been applied to the job-shop problem before, but often in a centrally calculated way where they are applied to the solution space, but they can be implemented in a bottom-up fashion to avoid global result computation as well. One of the problems in semiconductor production is that the production process requires a lot of switching between machines that process lots one after the other and machines that process batches of lots at once, often with long processing times. In this paper, we address this switching problem with the ``boids'' flocking algorithm that was originally used in robotics and movie industry. The flocking behavior is a bio-inspired algorithm that uses only local information and interaction based on simple heuristics. We show that this algorithm addresses these valid considerations in production plant optimization, as it reacts to the switching of machine kinds similar to how a swarm of flocking animals would react to obstacles in its course.

While stereotypes are well-documented in human social interactions, AI systems are often presumed to be less susceptible to such biases. Previous studies have focused on biases inherited from training data, but whether stereotypes can emerge spontaneously in AI agent interactions merits further exploration. Through a novel experimental framework simulating workplace interactions with neutral initial conditions, we investigate the emergence and evolution of stereotypes in LLM-based multi-agent systems. Our findings reveal that (1) LLM-Based AI agents develop stereotype-driven biases in their interactions despite beginning without predefined biases; (2) stereotype effects intensify with increased interaction rounds and decision-making power, particularly after introducing hierarchical structures; (3) these systems exhibit group effects analogous to human social behavior, including halo effects, confirmation bias, and role congruity; and (4) these stereotype patterns manifest consistently across different LLM architectures. Through comprehensive quantitative analysis, these findings suggest that stereotype formation in AI systems may arise as an emergent property of multi-agent interactions, rather than merely from training data biases. Our work underscores the need for future research to explore the underlying mechanisms of this phenomenon and develop strategies to mitigate its ethical impacts.

Model merging has emerged as an efficient strategy for constructing multitask models by integrating the strengths of multiple available expert models, thereby reducing the need to fine-tune a pre-trained model for all the tasks from scratch. Existing data-independent methods struggle with performance limitations due to the lack of data-driven guidance. Data-driven approaches also face key challenges: gradient-based methods are computationally expensive, limiting their practicality for merging large expert models, whereas existing gradient-free methods often fail to achieve satisfactory results within a limited number of optimization steps. To address these limitations, this paper introduces PSO-Merging, a novel data-driven merging method based on the Particle Swarm Optimization (PSO). In this approach, we initialize the particle swarm with a pre-trained model, expert models, and sparsified expert models. We then perform multiple iterations, with the final global best particle serving as the merged model. Experimental results on different language models show that PSO-Merging generally outperforms baseline merging methods, offering a more efficient and scalable solution for model merging.

-- Multi Robot Systems are increasingly deployed in applications, such as intralogistics or autonomous delivery, where multiple robots collaborate to complete tasks efficiently. One of the key factors enabling their efficient cooperation is Multi-Robot T ask Allocation (MRT A). Algorithms solving this problem optimize task distribution among robots to minimize the overall execution time. In shared environments, apart from the relative distance between the robots and the tasks, the execution time is also significantly impacted by the delay caused by navigating around moving people. However, most existing MRT A approaches are dynamics-agnostic, relying on static maps and neglecting human motion patterns, leading to inefficiencies and delays. In this paper, we introduce Human-A ware T ask Allocation (HA T A). This method leverages Maps of Dynamics (MoDs), spatio-temporal queryable models designed to capture historical human movement patterns, to estimate the impact of humans on the task execution time during deployment. HA T A utilizes a stochastic cost function that includes MoDs Experimental results show that integrating MoDs enhances task allocation performance, resulting in reduced mission completion times by up to 26% compared to the dynamics-agnostic method and up to 19% compared to the baseline. This work underscores the importance of considering human dynamics in MRT A within shared environments and presents an efficient framework for deploying multi-robot systems in environments populated by humans.

Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. However, the current fully autonomous paradigm poses potential safety risks when model understanding or reasoning capabilities are insufficient. To address this challenge, we first introduce \textbf{InquireBench}, a comprehensive benchmark specifically designed to evaluate mobile agents' capabilities in safe interaction and proactive inquiry with users, encompassing 5 categories and 22 sub-categories, where most existing VLM-based agents demonstrate near-zero performance. In this paper, we aim to develop an interactive system that actively seeks human confirmation at critical decision points. To achieve this, we propose \textbf{InquireMobile}, a novel model inspired by reinforcement learning, featuring a two-stage training strategy and an interactive pre-action reasoning mechanism. Finally, our model achieves an 46.8% improvement in inquiry success rate and the best overall success rate among existing baselines on InquireBench. We will open-source all datasets, models, and evaluation codes to facilitate development in both academia and industry.

Collaborative perception allows agents to enhance their perceptual capabilities by exchanging intermediate features. Existing methods typically organize these intermediate features as 2D bird's-eye-view (BEV) representations, which discard critical fine-grained 3D structural cues essential for accurate object recognition and localization. To this end, we first introduce point-level tokens as intermediate representations for collaborative perception. However, point-cloud data are inherently unordered, massive, and position-sensitive, making it challenging to produce compact and aligned point-level token sequences that preserve detailed structural information. Therefore, we present CoPLOT, a novel Collaborative perception framework that utilizes Point-Level Optimized Tokens. It incorporates a point-native processing pipeline, including token reordering, sequence modeling, and multi-agent spatial alignment. A semantic-aware token reordering module generates adaptive 1D reorderings by leveraging scene-level and token-level semantic information. A frequency-enhanced state space model captures long-range sequence dependencies across both spatial and spectral domains, improving the differentiation between foreground tokens and background clutter. Lastly, a neighbor-to-ego alignment module applies a closed-loop process, combining global agent-level correction with local token-level refinement to mitigate localization noise. Extensive experiments on both simulated and real-world datasets show that CoPLOT outperforms state-of-the-art models, with even lower communication and computation overhead. Code will be available at https://github.com/CheeryLeeyy/CoPLOT.

Generative artificial intelligence in music has made significant strides, yet it still falls short of the substantial achievements seen in natural language processing, primarily due to the limited availability of music data. Knowledge-informed approaches have been shown to enhance the performance of music generation models, even when only a few pieces of musical knowledge are integrated. This paper seeks to leverage comprehensive music theory in AI-driven music generation tasks, such as algorithmic composition and style transfer, which traditionally require significant manual effort with existing techniques. We introduce a novel automatic music lexicon construction model that generates a lexicon, named CompLex, comprising 37,432 items derived from just 9 manually input category keywords and 5 sentence prompt templates. A new multi-agent algorithm is proposed to automatically detect and mitigate hallucinations. CompLex demonstrates impressive performance improvements across three state-of-the-art text-to-music generation models, encompassing both symbolic and audio-based methods. Furthermore, we evaluate CompLex in terms of completeness, accuracy, non-redundancy, and executability, confirming that it possesses the key characteristics of an effective lexicon.