English
Related papers

Related papers: Exploratory Retrieval-Augmented Planning For Conti…

200 papers

The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a better-than-random exploration policy or a safe-guard against…

Artificial Intelligence · Computer Science 2022-07-08 Shivansh Beohar , Andrew Melnik

Long-horizon embodied planning underpins embodied AI. To accomplish long-horizon tasks, one of the most feasible ways is to decompose abstract instructions into a sequence of actionable steps. Foundation models still face logical errors and…

Robotics · Computer Science 2025-03-14 Siyuan Liu , Jiawei Du , Sicheng Xiang , Zibo Wang , Dingsheng Luo

Reinforcement Learning (RL) agents often struggle in sparse-reward environments where traditional exploration strategies fail to discover effective action sequences. Large Language Models (LLMs) possess procedural knowledge and reasoning…

Machine Learning · Computer Science 2025-10-13 Vaibhav Jain , Gerrit Grossmann

We introduce Plan*RAG, a novel framework that enables structured multi-hop reasoning in retrieval-augmented generation (RAG) through test-time reasoning plan generation. While existing approaches such as ReAct maintain reasoning chains…

Computation and Language · Computer Science 2025-02-05 Prakhar Verma , Sukruta Prakash Midigeshi , Gaurav Sinha , Arno Solin , Nagarajan Natarajan , Amit Sharma

In complex embodied long-horizon manipulation tasks, effective task decomposition and execution require synergistic integration of textual logical reasoning and visual-spatial imagination to ensure efficient and accurate operation. Current…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Xinyan Cai , Shiguang Wu , Dafeng Chi , Yuzheng Zhuang , Xingyue Quan , Jianye Hao , Qiang Guan

Coordinating navigation and manipulation with robust performance is essential for embodied AI in complex indoor environments. However, as tasks extend over long horizons, existing methods often struggle due to catastrophic forgetting,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Jingjing Qian , Zeyuan He , Chen Shi , Lei Xiao , Li Jiang

Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments. Recent large language models (LLM) can embed rich semantic knowledge for agents in plan…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Zhenyu Wu , Ziwei Wang , Xiuwei Xu , Jiwen Lu , Haibin Yan

Multimodal Large Language Models (MLLMs) have empowered embodied agents with remarkable capabilities in planning and reasoning. However, when facing ambiguous natural language instructions (e.g., "fetch the tool" in a cluttered room),…

Artificial Intelligence · Computer Science 2025-12-23 Weijie Zhou , Xuangtang Xiong , Ye Tian , Lijun Yue , Xinyu Wu , Wei Li , Chaoyang Zhao , Honghui Dong , Ming Tang , Jinqiao Wang , Zhengyou Zhang

We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user…

Computation and Language · Computer Science 2026-05-13 Ariel Gera , Shir Ashury-Tahan , Gal Bloch , Ohad Eytan , Assaf Toledo

In embodied artificial intelligence, enabling heterogeneous robot teams to execute long-horizon tasks from high-level instructions remains a critical challenge. While large language models (LLMs) show promise in instruction parsing and…

Robotics · Computer Science 2026-03-06 Haishan Zeng , Mengna Wang , Peng Li

There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhorse of large-scale…

Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We…

Artificial Intelligence · Computer Science 2024-04-05 Benedict Quartey , Ankit Shah , George Konidaris

Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an…

Robotics · Computer Science 2025-03-24 Zixuan Wang , Bo Yu , Junzhe Zhao , Wenhao Sun , Sai Hou , Shuai Liang , Xing Hu , Yinhe Han , Yiming Gan

Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental…

Artificial Intelligence · Computer Science 2026-05-14 Yuxin Liu , Ziang Ye , Yueqing Sun , Mingye Zhu , Jinwei Xiao , Zhuowen Han , Qi GU , Xunliang Cai , Lei Zhang

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Machine Learning · Computer Science 2026-02-17 Taiwei Shi , Sihao Chen , Bowen Jiang , Linxin Song , Longqi Yang , Jieyu Zhao

Procedure Planning in instructional videos entails generating a sequence of action steps based on visual observations of the initial and target states. Despite the rapid progress in this task, there remain several critical challenges to be…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Ali Zare , Yulei Niu , Hammad Ayyubi , Shih-fu Chang

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…

Computation and Language · Computer Science 2025-05-20 Zhangyu Wang , Siyuan Gao , Rong Zhou , Hao Wang , Li Ning

In this work, we consider the problem of autonomous exploration in search of targets while respecting a fixed energy budget. The robot is equipped with an incremental-resolution symbolic perception module wherein the perception of targets…

Robotics · Computer Science 2023-09-15 Disha Kamale , Sofie Haesaert , Cristian-Ioan Vasile

Embodied robotic AI systems designed to manage complex daily tasks rely on a task planner to understand and decompose high-level tasks. While most research focuses on enhancing the task-understanding abilities of LLMs/VLMs through…

Robotics · Computer Science 2025-12-23 Zhenglong Guo , Yiming Zhao , Feng Jiang , Heng Jin , Zongbao Feng , Jianbin Zhou , Siyuan Xu

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous…

Machine Learning · Computer Science 2026-02-10 Dilip Arumugam , Thomas L. Griffiths