Related papers: REDSearcher: A Scalable and Cost-Efficient Framewo…

LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions, or maintain global awareness under long contexts, often…

Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively. Nevertheless, due to their limited capabilities in reasoning and search, their performance on multi-hop QA…

Conventional Retrieval Augmented Generation (RAG) approaches are common in text-based applications. However, they struggle with structured, interconnected datasets like knowledge graphs, where understanding underlying relationships is…

Can scaling transform reasoning? In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a slow-thinking model, RedStar. Through extensive experiments…

The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches…

While recent advances in reasoning models have demonstrated cognitive behaviors through reinforcement learning, existing approaches struggle to invoke deep reasoning capabilities in multi-turn agents with long-horizon interactions. We…

With recent advancements in large language models, methods like chain-of-thought prompting to elicit reasoning chains have been shown to improve results on reasoning tasks. However, tasks that require multiple steps of reasoning still pose…

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant…

This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics by addressing the inherent limitations of the Parallel Scaling paradigm. Our system utilizes two key…

Large language models (LLMs) are incredible and versatile tools for text-based tasks that have enabled countless, previously unimaginable, applications. Retrieval models, in contrast, have not yet seen such capable general-purpose models…

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of…

Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to-date information. While enabling LLMs to interact with…

People commonly leverage structured content to accelerate knowledge acquisition and research problem solving. Among these, roadmaps guide researchers through hierarchical subtasks to solve complex research problems step by step. Despite…

Retrieval-Augmented Language Models (RALMs) represent a classic paradigm where models enhance generative capabilities using external knowledge retrieved via a specialized module. Recent advancements in Agent techniques enable Large Language…

Large language models (LLMs) with extended context windows enable tasks requiring extensive information integration but are limited by the scarcity of high-quality, diverse datasets for long-context instruction tuning. Existing data…

We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200,000 tokens. We provide a training recipe for efficiently extending context length of LLMs. We identify that the critical element in…

Recent advances have showcased the extraordinary capabilities of Large Language Model (LLM) agents in tackling web-based information-seeking tasks. However, existing efforts mainly focus on single-fact retrieval and rely on outcome-only…