Related papers: HiRAS: A Hierarchical Multi-Agent Framework for Pa…
Retrieval-augmented generation (RAG) has rapidly advanced the language model field, particularly in question-answering (QA) systems. By integrating external documents during the response generation phase, RAG significantly enhances the…
Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. To address these…
Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective…
The exponential growth of scientific knowledge has made the automated generation of scientific hypotheses that combine novelty, feasibility, and research value a core challenge. Existing methods based on large language models fail to…
Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with…
The rapid accumulation of Earth science data has created a significant scalability challenge; while repositories like PANGAEA host vast collections of datasets, citation metrics indicate that a substantial portion remains underutilized,…
It has been widely recognized that the performance of a multi-agent system is highly affected by its organization. A large scale system may have billions of possible ways of organization, which makes it impractical to find an optimal choice…
Large Language Model (LLM) agents have demonstrated remarkable capabilities in organizing and executing complex tasks, and many such agents are now widely used in various application scenarios. However, developing these agents requires…
Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…
Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance,…
Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing…
Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks. However, existing RAG methods do not adequately utilize the naturally inherent…
Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While…
Keeping pace with the rapid growth of academia literature presents a significant challenge for researchers, funding bodies, and academic societies. To address the time-consuming manual effort required for scholarly discovery, we present a…
Increased reproducibility of machine learning research has been a driving force for dramatic improvements in learning performances. The scientific community further fosters this effort by including reproducibility ratings in reviewer forms…
Purpose: The purpose of this paper is to propose a tool that generates authority files to be integrated with linked data by means of learning rules. AUTHORIS is software developed to enhance authority control and information exchange among…
This technical brief introduces Deep Agent, an advanced autonomous AI system designed to manage complex multi-phase tasks through a novel hierarchical task management architecture. The system's foundation is built on our Hierarchical Task…
Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks…
Constructing behavioral-level chiplet models (e.g., SystemC) is crucial for early-stage heterogeneous architecture exploration. Traditional manual modeling is notoriously time-consuming and error-prone. Recently, Large Language Models…
In the domain of combat simulations in support of wargaming, the development of intelligent agents has predominantly been characterized by rule-based, scripted methodologies with deep reinforcement learning (RL) approaches only recently…