Related papers: Reinforced Collaboration in Multi-Agent Flow Netwo…

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

Most real-world domains can be formulated as multi-agent (MA) systems. Intentionality sharing agents can solve more complex tasks by collaborating, possibly in less time. True cooperative actions are beneficial for egoistic and collective…

Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the…

In disaster scenarios, establishing robust emergency communication networks is critical, and unmanned aerial vehicles (UAVs) offer a promising solution to rapidly restore connectivity. However, organizing UAVs to form multi-hop networks in…

Data wrangling is a time-consuming and challenging task in a data science pipeline. While many tools have been proposed to automate or facilitate data wrangling, they often misinterpret user intent, especially in complex tasks. We propose…

Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning hallucinations and require…

Multi-agent systems (MAS) increasingly solve complex tasks by orchestrating agents and tools selected from rapidly growing marketplaces. As these marketplaces expand, many candidates become functionally overlapping, making selection not…

Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic,…

Retrieval-augmented generation (RAG) is widely utilized to incorporate external knowledge into large language models, thereby enhancing factuality and reducing hallucinations in question-answering (QA) tasks. A standard RAG pipeline…

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in…

With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large quantity of retrieved knowledge to solve complex tasks. However, the limited context window…

With an ever-growing zoo of LLMs and benchmarks, the need to orchestrate multiple models for improved task performance has never been more pressing. While frameworks like Mixture-of-Agents (MoA) attempt to coordinate LLMs, they often fall…

*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior of other agents. No methods have been proposed for…

This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, which learn to communicate and cooperate. We provide an overview of this emerging field, with…

Multi-agent systems (MAS) built on large language models (LLMs) have shown strong performance across many tasks. Most existing approaches improve only one aspect at a time, such as the communication topology, role assignment, or LLM…

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation,…

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing…

In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…

Creating end-to-end bioinformatics workflows requires diverse domain expertise, which poses challenges for both junior and senior researchers as it demands a deep understanding of both genomics concepts and computational techniques. While…