Related papers: $A^2Flow:$ Automating Agentic Workflow Generation …

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Most existing Large Language Model (LLM)-based Multi-Agent Systems (MAS) rely on predefined workflows, where human engineers enumerate task states in advance and specify routing rules and contextual injections accordingly. Such…

Autonomous data science, from raw data sources to analyst-grade deep research reports, has been a long-standing challenge, and is now becoming feasible with the emergence of powerful large language models (LLMs). Recent workflow-based data…

While many researchers use Large Language Models (LLMs) through chat-based access, their real potential lies in leveraging LLMs via application programming interfaces (APIs). This paper conceptualizes LLMs as universal text processing…

At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely…

We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs).…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large language models (LLMs) to automate data preparation from…

Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models into this framework poses unique challenges. In particular,…

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack…

Visual analytics (VA) workflows are inherently complex, involving data transformation, feature engineering, visual representation, and human interpretation. They are typically described in unstructured prose, hindering systematic…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in…

The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for the automated…

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

Traditional control system design, reliant on expert knowledge and precise models, struggles with complex, nonlinear, or uncertain dynamics. This paper introduces AgenticControl, a novel multi-agent framework that automates controller…

Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into…

Multi-agent systems (MAS) have emerged as a powerful paradigm for orchestrating large language models (LLMs) and specialized tools to collaboratively address complex tasks. However, existing MAS frameworks often require manual workflow…