Related papers: A-MapReduce: Executing Wide Search via Agentic Map…

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…

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…

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…

With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve-then-generate paradigm toward more sophisticated agentic…

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,…

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform…

Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts…

Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative…

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…

Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…

Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints,…

Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous information and high token costs associated with multimodal inputs…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document…

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…

Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where…

Recent significant advances in integrating multiple Large Language Model (LLM) systems have enabled Agentic Frameworks capable of performing complex tasks autonomously, including novel scientific research. We develop and demonstrate such a…

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the…