paper-with-me

Papers

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent

2026-04-20 · Wanli Li, Bince Qu, Bo Pan, Jianyu Zhang, Zheng Liu, Pan Zhang, Wei Chen, Bo Zhang arxiv

Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine real-world search capabilities, and real-world search dependency during RL training introduces instability and prohibitive cost, which limits the scalability of Agentic RL. LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively, demonstrating that scalable RL training is a key enabler for Deep Research Agents.

📄 PDF Abstract BibTeX arXiv:2604.17931

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Tongyi DeepResearch Technical Report

2025-10-28 · Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang 외 arxiv

We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResear…

MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments

2026-06-18 · Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang 외 arxiv

Deep research agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-…

Reinforcement Learning

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

2026-06-13 · Ang Li, Ben Liu, Bin Han, Bin Hu 외 arxiv

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present …

Reinforcement LearningResponse Generation

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

2026-07-22 · Jian Hu, Huiying Li, Hao Zhang, Binfeng Xu 외 hf

Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstream frameworks each change threads through layers of trainer, distribute…

Reinforcement Learning

Internet of Agentic AI: Incentive-Compatible Distributed Teaming and Workflow

2026-02-03 · Ya-Ting Yang, Quanyan Zhu arxiv

Large language models (LLMs) have enabled a new class of agentic AI systems that reason, plan, and act by invoking external tools. However, most existing agentic architectures remain centralized and monolithic, limiting …