Related papers: MAS-Orchestra: Understanding and Improving Multi-A…
Misalignment in Multi-Agent Systems (MAS) is frequently treated as a technical failure. Yet, issues may arise from the conceptual design phase, where semantic ambiguity and normative projection occur. The Rabbit-Duck illusion illustrates…
Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, fostering a promising hybrid paradigm for MLLM-based mobile automation. However, systematic evaluation of GUI-shortcut hybrid agents…
Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a single context window comes with a well-known cost: as tool specifications and…
Recent progress in language modeling has largely relied on scaling model size, yet larger models do not reliably improve performance on tasks requiring multi-step reasoning and tool use. Multi-agent collaboration offers a potential…
Multi-agent systems (MAS) composed of large language models often exhibit improved problem-solving performance despite operating on identical information. In this work, we provide a formal explanation for this phenomenon grounded in…
Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability…
LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that…
Recent advancements in Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) have demonstrated tremendous potential in diverse task scenarios. Nonetheless, existing agentic systems typically rely on predefined agent-role design…
Multi-Agent Systems (MAS) built using AI agents fulfill a variety of user intents that may be used to design and build a family of related applications. However, the creation of such MAS currently involves manual composition of the plan,…
As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework…
Multi-agent systems (MAS) have recently emerged as promising socio-collaborative companions for emotional and cognitive support. However, these systems frequently suffer from persona collapse--where agents revert to generic, homogenized…
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…
Time series analysis underpins many real-world applications, yet existing time-series-specific methods and pretrained large-model-based approaches remain limited in integrating intuitive visual reasoning and generalizing across tasks with…
Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often…
Multi-agent coordination studies the underlying mechanism enabling the trending spread of diverse multi-agent systems (MAS) and has received increasing attention, driven by the expansion of emerging applications and rapid AI advances. This…
While Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning tasks through collaborative interaction, optimizing their dynamics remains a formidable challenge due to the discrete, non-differentiable nature of…
Orchestrated multi-agent systems represent the next stage in the evolution of artificial intelligence, where autonomous agents collaborate through structured coordination and communication to achieve complex, shared objectives. This paper…
Large Language Model (LLM)-based Multi-Agent Systems (MAS) enhance complex problem solving through multi-agent collaboration, but often incur substantially higher costs than single-agent systems. Recent MAS routing methods aim to balance…
Multiagent Systems (MASs) involve different characteristics, such as autonomy, asynchronous and social features, which make these systems more difficult to understand. Thus, there is a lack of procedures guaranteeing that multiagent systems…
The increased complexity and dynamism of present and future Multi-Agent Systems (MAS) enforce the need for considering both of their static (design-time) and the dynamic (run-time) aspects. A type of balance between the two aspects can…