13 papers
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Hongjin Qian, Chaofan Li, Kun Luo +11
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rest…
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and ve…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
Zhang Zhang, Shuqi Lu, Hongjin Qian +2
Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflection…
MemoBrain: Executive Memory as an Agentic Brain for Reasoning
Hongjin Qian, Zhao Cao, Zheng Liu
Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working…
General Agentic Memory Via Deep Research
B. Y. Yan, Chaofan Li, Hongjin Qian +2
Memory is critical for AI agents, yet the widely-adopted static memory, aiming to create readily available memory in advance, is inevitably subject to severe information loss. To a…
InfoFlow: Reinforcing Search Agent Via Reward Density Optimization
Kun Luo, Hongjin Qian, Zheng Liu +5
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward De…
Model-Document Protocol for AI Search
Hongjin Qian, Zheng Liu
AI search depends on linking large language models (LLMs) with vast external knowledge sources. Yet web pages, PDF files, and other raw documents are not inherently LLM-ready: they…
MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning
Hongjin Qian, Zheng Liu
In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-im…
Open Data Synthesis For Deep Research
Ziyi Xia, Kun Luo, Hongjin Qian +1
Large language models (LLMs) are increasingly expected to go beyond simple factual queries toward Deep Research-tasks that require decomposing questions into sub-problems, coordina…
Integrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction
Bao Zhang, Zihan Li, Zhenglei Liu +2
Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, tra…
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
Yutao Zhu, Jiajie Jin, Hongjin Qian +3
Existing studies have optimized retrieval-augmented generation (RAG) across various sub-tasks, such as query understanding and retrieval refinement, but integrating these optimizat…
Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
Hongjin Qian, Zheng Liu
Augmenting large language models (LLMs) with external retrieval has become a standard method to address their inherent knowledge cutoff limitations. However, traditional retrieval-…