Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks. However, they face two critical failure modes as the accumulating context becomes flooded with both crucial evidence and irrelevant information: (1) ineffective search chain construction that produces incorrect queries or omits retrieval of critical information, and (2) reasoning hijacking by peripheral evidence that causes models to misidentify distractors as valid evidence. To address these challenges, we propose **D$^2$Plan**, a **D**ual-agent **D**ynamic global **Plan**ning paradigm for complex retrieval-augmented reasoning. **D$^2$Plan** operates through the collaboration of a *Reasoner* and a *Purifier*: the *Reasoner* constructs explicit global plans during reasoning and dynamically adapts them based on retrieval feedback; the *Purifier* assesses retrieval relevance and condenses key information for the *Reasoner*. We further introduce a two-stage training framework consisting of supervised fine-tuning (SFT) cold-start on synthesized trajectories and RL with plan-oriented rewards to teach LLMs to master the **D$^2$Plan** paradigm. Extensive experiments demonstrate that **D$^2$Plan** enables more coherent multi-step reasoning and stronger resilience to irrelevant information, thereby achieving superior performance on challenging QA benchmarks.
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics
Automation and Control Institute, Faculty of Electrical Engineering, TU Wien(自动化与控制研究所,电气工程学院,维也纳技术大学);AIT Austrian Institute of Technology GmbH, Center for Vision, Automation and Control(奥地利技术研究所(AIT)有限公司,视觉、自动化与控制中心)
KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
Zhejiang University(浙江大学);ZJU-Ant Group Joint Research Center for Knowledge Graphs(浙江大学-蚂蚁集团知识图谱联合研究中心);Ant Group(蚂蚁集团);National University of Singapore(新加坡国立大学)
Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
Tongji University(同济大学);Shanghai AI Laboratory(上海人工智能实验室);Harbin Institute of Technology(哈尔滨工业大学);Fudan University(复旦大学);Skywork AI;University of California, Santa Cruz(加州大学圣克鲁兹分校);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学)
Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planning
School of Mechanical, Aerospace, and Manufacturing Engineering University of Connecticut Storrs, Connecticut, USA(机械、航空航天与制造工程学院 美国康涅狄格大学 斯托尔斯分校);The United States Army Combat Capabilities Development Command Ground Vehicle Systems Center Warren, Michigan, USA(美国陆军作战能力发展司令部地面车辆系统中心 华伦,密歇根州,美国)
LLM-Augmented Chemical Synthesis and Design Decision Programs
École Polytechnique Fédérale de Lausanne (EPFL)(瑞士联邦理工学院洛桑校区);National Centre of Competence in Research (NCCR) Catalysis(催化领域竞争力研究国立中心);Harvard University(哈佛大学);Cornell University(康奈尔大学)
LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Chinese Academy of Sciences(中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
University of Chinese Academy of Sciences(中国科学院大学);MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所MAIS部);Wenge Technology Co., Ltd(Wenger科技有限公司)
P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)