English
Related papers

Related papers: Do Agents Need to Plan Step-by-Step? Rethinking Pl…

200 papers

Long-horizon AI agents execute complex workflows spanning hundreds of sequential actions, yet a single wrong assumption early on can cascade into irreversible errors. When instructions are incomplete, the agent must decide not only whether…

Computation and Language · Computer Science 2026-05-11 Anmol Gulati , Hariom Gupta , Elias Lumer , Sahil Sen , Vamse Kumar Subbiah

Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods struggle with complex, long-horizon tasks because they…

Artificial Intelligence · Computer Science 2026-02-11 Jae-Woo Choi , Hyungmin Kim , Hyobin Ong , Youngwoo Yoon , Minsu Jang , Dohyung Kim , Jaehong Kim

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

Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become stronger, the main bottleneck shifts from local skill execution to maintaining a coherent…

Robotics · Computer Science 2026-05-20 Shuhan Guo , Kun Zhang , Haifei Liu , Xingyu Gao , Yongqi Zhang , Yaqing Wang , Quanming Yao

Many applications involving complex multi-task problems such as disaster relief, logistics and manufacturing necessitate the deployment and coordination of heterogeneous multi-agent systems due to the sheer number of tasks that must be…

Multiagent Systems · Computer Science 2020-04-07 Yousef Emam , Sean Wilson , Mathias Hakenberg , Ulrich Munz , Magnus Egerstedt

Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…

Artificial Intelligence · Computer Science 2025-10-22 Abhigya Verma , Seganrasan Subramanian , Nandhakumar Kandasamy , Naman Gupta

Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether…

Artificial Intelligence · Computer Science 2026-05-26 Yuyang Hu , Hongjin Qian , Shuting Wang , Jiongnan Liu , Tong Zhao , Xiaoxi Li , Zheng Liu , Zhicheng Dou

How-to procedures, such as how to plant a garden, are now used by millions of users, but sometimes need customizing to meet a user's specific needs, e.g., planting a garden without pesticides. Our goal is to measure and improve an LLM's…

Computation and Language · Computer Science 2024-06-03 Yash Kumar Lal , Li Zhang , Faeze Brahman , Bodhisattwa Prasad Majumder , Peter Clark , Niket Tandon

Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent…

Artificial Intelligence · Computer Science 2026-05-01 Jinbiao Wei , Kangqi Ni , Yilun Zhao , Guo Gan , Arman Cohan

Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning). Humans can generate and execute plans with…

Machine Learning · Computer Science 2023-11-10 Bharat Prakash , Tim Oates , Tinoosh Mohsenin

ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a…

Cryptography and Security · Computer Science 2026-05-15 Julien Piet , Annabella Chow , Yiwei Hou , Muxi Lyu , Sylvie Venuto , Jinhao Zhu , Raluca Ada Popa , David Wagner

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing…

Artificial Intelligence · Computer Science 2025-08-18 Yanming Liu , Xinyue Peng , Jiannan Cao , Yuwei Zhang , Xuhong Zhang , Sheng Cheng , Xun Wang , Jianwei Yin , Tianyu Du

Large language model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long horizon navigation, large scale information…

Artificial Intelligence · Computer Science 2025-10-09 Jingbo Yang , Bairu Hou , Wei Wei , Shiyu Chang , Yujia Bao

Open world language conditioned task planning is crucial for robots operating in large-scale household environments. While many recent works attempt to address this problem using Large Language Models (LLMs) via prompting or training, a key…

Robotics · Computer Science 2026-02-13 Zhihong Liu , Yang Li , Rengming Huang , Cewu Lu , Panpan Cai

Efficient coordination and planning is essential for large-scale multi-agent systems that collaborate in a shared dynamic environment. Heuristic search methods or learning-based approaches often lack the guarantee on correctness and…

Robotics · Computer Science 2024-04-10 Zesen Liu , Meng Guo , Weimin Bao , Zhongkui Li

Lifelong Multi-Agent Path Finding (MAPF) is critical for modern warehouse automation, which requires multiple robots to continuously navigate conflict-free paths to optimize the overall system throughput. However, the complexity of…

Artificial Intelligence · Computer Science 2026-03-26 Han Zheng , Yining Ma , Brandon Araki , Jingkai Chen , Cathy Wu

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…

Machine Learning · Computer Science 2026-05-12 Jiangweizhi Peng , Yuanxin Liu , Ruida Zhou , Charles Fleming , Zhaoran Wang , Alfredo Garcia , Mingyi Hong

The ability of Language Models (LMs) to understand natural language makes them a powerful tool for parsing human instructions into task plans for autonomous robots. Unlike traditional planning methods that rely on domain-specific knowledge…

We present a novel algorithm for large-scale Multi-Agent Path Finding (MAPF) that enables fast, scalable planning in dynamic environments such as automated warehouses. Our approach introduces finite-horizon hierarchical factorization, a…

Robotics · Computer Science 2025-05-13 Jiarui Li , Alessandro Zanardi , Gioele Zardini

Sequential decision-making and motion planning for robotic manipulation induce combinatorial complexity. For long-horizon tasks, especially when the environment comprises many objects that can be interacted with, planning efficiency becomes…

Robotics · Computer Science 2022-03-08 Cornelius V. Braun , Joaquim Ortiz-Haro , Marc Toussaint , Ozgur S. Oguz