English
Related papers

Related papers: LHAW: Controllable Underspecification for Long-Hor…

200 papers

Large Language Models (LLMs) have facilitated the definition of autonomous intelligent agents. Such agents have already demonstrated their potential in solving complex tasks in different domains. And they can further increase their…

Software Engineering · Computer Science 2025-06-30 Adem Ait , Javier Luis Cánovas Izquierdo , Jordi Cabot

Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These…

Successfully solving long-horizon manipulation tasks remains a fundamental challenge. These tasks involve extended action sequences and complex object interactions, presenting a critical gap between high-level symbolic planning and…

Robotics · Computer Science 2025-09-29 Jialiang Li , Wenzheng Wu , Gaojing Zhang , Yifan Han , Wenzhao Lian

Reasoning over heterogeneous artifacts (PDFs, spreadsheets, slide decks, etc.) increasingly occurs within structured agent workflows that iteratively extract, transform, and reference external information. In these workflows, uncertainty is…

Artificial Intelligence · Computer Science 2026-05-01 Anna Mazhar , Huzaifa Suri , Sainyam Galhotra

As Large Language Models increasingly automate complex, long-horizon tasks such as \emph{vibe coding}, a supervision gap has emerged. While models excel at execution, users often struggle to guide them effectively due to insufficient domain…

Artificial Intelligence · Computer Science 2026-02-09 Enyu Zhou , Zhiheng Xi , Long Ma , Zhihao Zhang , Shihan Dou , Zhikai Lei , Guoteng Wang , Rui Zheng , Hang Yan , Tao Gui , Qi Zhang , Xuanjing Huang

As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing their capabilities in increasingly complex and diverse tasks.…

Computation and Language · Computer Science 2026-03-06 Yurun Chen , Xavier Hu , Yuhan Liu , Ziqi Wang , Zeyi Liao , Lin Chen , Feng Wei , Yuxi Qian , Bo Zheng , Keting Yin , Shengyu Zhang

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks,…

Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external…

Computation and Language · Computer Science 2024-07-19 Zelong Li , Shuyuan Xu , Kai Mei , Wenyue Hua , Balaji Rama , Om Raheja , Hao Wang , He Zhu , Yongfeng Zhang

Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degrade performance, and opaque execution traces make failures…

Artificial Intelligence · Computer Science 2026-02-17 Salaheddin Alzu'bi , Baran Nama , Arda Kaz , Anushri Eswaran , Weiyuan Chen , Sarvesh Khetan , Rishab Bala , Tu Vu , Sewoong Oh

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient…

Artificial Intelligence · Computer Science 2026-05-26 Yuxin Zhang , Mengxue Hu , Zheng Lin , Xiaoyi Fan , Fan Xie , Zihan Fang , Jing Yang , Wenjun Zhu , Zhiwen Chen , Chengfei Lv , Zhe Chen

Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating the operator's intent into coordinated swarm actions and helping determine when…

Robotics · Computer Science 2026-05-11 Junfeng Chen , Yuxiao Zhu , An Zhuo , Xintong Zhang , Shuo Zhang , Guanghui Wen , Xiwang Dong , Meng Guo , Zhongkui Li

Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often leads to myopic…

Artificial Intelligence · Computer Science 2026-05-26 Oguzhan Gungordu , Siheng Xiong , Faramarz Fekri

Large Language Models (LLMs) have shown promise as robotic planners but often struggle with long-horizon and complex tasks, especially in specialized environments requiring external knowledge. While hierarchical planning and…

Artificial Intelligence · Computer Science 2025-04-08 Cristina Cornelio , Flavio Petruzzellis , Pietro Lio

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle…

Robotics · Computer Science 2026-04-16 Zhen Liu , Xinyu Ning , Zhe Hu , Xinxin Xie , Weize Li , Zhipeng Tang , Chongyu Wang , Zejun Yang , Hanlin Wang , Yitong Liu , Zhongzhu Pu

Workflows play a crucial role in enhancing enterprise efficiency by orchestrating complex processes with multiple tools or components. However, hand-crafted workflow construction requires expert knowledge, presenting significant technical…

Computation and Language · Computer Science 2025-03-31 Hanchao Liu , Rongjun Li , Weimin Xiong , Ziyu Zhou , Wei Peng

We consider enhancing large language models (LLMs) for complex planning tasks. While existing methods allow LLMs to explore intermediate steps to make plans, they either depend on unreliable self-verification or external verifiers to…

Artificial Intelligence · Computer Science 2025-02-27 Hongyi Ling , Shubham Parashar , Sambhav Khurana , Blake Olson , Anwesha Basu , Gaurangi Sinha , Zhengzhong Tu , James Caverlee , Shuiwang Ji

Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into…

Robotics · Computer Science 2025-06-03 Yi Yang , Jiaxuan Sun , Siqi Kou , Yihan Wang , Zhijie Deng

Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as Group Relative Policy Optimization (GRPO), encounter two…

Machine Learning · Computer Science 2026-03-11 Hui-Ze Tan , Xiao-Wen Yang , Hao Chen , Jie-Jing Shao , Yi Wen , Yuteng Shen , Weihong Luo , Xiku Du , Lan-Zhe Guo , Yu-Feng Li

Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only…

Artificial Intelligence · Computer Science 2026-03-23 Beibei Xu , Yutong Ye , Chuyun Shen , Yingbo Zhou , Cheng Chen , Mingsong Chen

Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments.…