Related papers: Atomizer: An LLM-based Collaborative Multi-Agent F…

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models…

The task of atom rearrangement has emerged in the last decade as a fundamental building block for the development of neutral atom-based quantum processors. However, despite many recent efforts to develop algorithms with favorable asymptotic…

Large Language Models (LLMs) have demonstrated remarkable capabilities in solving various tasks, yet they often struggle with comprehensively addressing complex and vague problems. Existing approaches, including multi-agent LLM systems,…

With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large…

Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and…

Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through…

Atomic decomposition -- breaking a candidate answer into claims before verifying each against a reference -- is a widely adopted design for LLM-based reference-grounded judges. However, atomic prompts are typically richer and longer, making…

Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms. Traditional reranking models have focused predominantly on accuracy, but modern applications demand…

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy,…

Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but…

Large language models (LLMs) and agent techniques have brought a fundamental shift in the functionality and development paradigm of data analysis tasks (a.k.a LLM/Agent-as-Data-Analyst), demonstrating substantial impact across both academia…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of "slow thinking" into multimodal large language models (MLLMs). Our core idea is that different levels of reasoning abilities…

Query-focused summarization over multi-table data is a challenging yet critical task for extracting precise and relevant information from structured data. Existing methods often rely on complex preprocessing steps and struggle to generalize…

Large language models (LLMs) have large potential for molecular optimization, as they can gather external chemistry tools and enable collaborative interactions to iteratively refine molecular candidates. However, this potential remains…

Chain-of-Thought (CoT) Prompting is a dominant paradigm in Large Language Models (LLMs) to enhance complex reasoning. It guides LLMs to present multi-step reasoning, rather than generating the final answer directly. However, CoT encounters…

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up…

Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-world scenarios, cooperation among individuals is often…

Smart contracts are a core component of blockchain technology and are widely deployed across various scenarios. However, atomicity violations have become a potential security risk. Existing analysis tools often lack the precision required…