Long-Horizon Agent Tasks

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 125% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 127

All topics

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning
Aug 8, 2026Keyang Zhong, Kuo Wang, Peng Liu +5Temporal Video Grounding Group Relative Policy Optimization
Sun Yat-sen University · Shenzhen Loop Area Institute · Guangdong OPPO Mobile Telecommunications Corp., Ltd. +2
MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
Aug 7, 2026Zhisheng Chen, Bingfan Zeng, Bangde Cao +8Long-Horizon Agent Tasks Memory-Augmented Agents
Nanyang Technological University · South China University of Technology · Beijing University of Posts and Telecommunications +5
Online Monitoring and Corrective Steering of Programming Agents
Aug 7, 2026Shuyang Liu, Saman Dehghan, Ji Young Kim +3Software Engineering Agents LLM Agent Workflow Optimization
University of Illinois Urbana-Champaign, USA · IBM, USA
The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents
Aug 7, 2026Mingguang Chen, Licheng Wang, Bo QuLong-Horizon Planning Long-Horizon Agent Evaluation
1DeepGrounding · 2AlphaAvatar
Recursive Synthesis for Long-Horizon Terminal Tasks
Aug 5, 2026Zhongzhi Li, Yucheng Shi, Zongxia Li +8Terminal Agents Synthetic Benchmark Generation
Tencent HY LLM Frontier · University of Georgia · University of Maryland, College Park +5
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
Aug 5, 2026Xuying Ning, Dongqi Fu, Tianxin Wei +17Agent Harness Optimization Long-Horizon Agent Tasks
University of Illinois Urbana–Champaign · Meta AI
Mimir: A Neuro-Symbolic Memory System with Dynamic Grounding for Embodied Agents in Interactive Environments
Aug 5, 2026Haoming Xu, Zhenlin He, Hengyi Wang +2Neuro-Symbolic Reasoning Long-Horizon Agent Tasks
PrimeBot Research Institute · Peking University
Project2Task: Graph-Guided Project-Level Planning for Autonomous Research
Aug 5, 2026Huirui Xu, Runtao Xu, Shuo Ren +1AI Agents for Scientific Discovery Graph-Based Planning
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · School of Future Technology, University of Chinese Academy of Sciences +1
Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit
Aug 3, 2026Jingxi WeiLLM Agent Training Long-Horizon Agent Tasks
EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents
Aug 3, 2026Yuxi Qian, Yuxiang RenAgent Memory Graph-Based Agent Memory
Towards the Harness of Embodied Agents
Aug 3, 2026Qi Wang, Tianyi Wang, Chengyang Li +6Tool-Using Agents Long-Horizon Agent Tasks
Eastern Institute of Technology, Ningbo
Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer
Aug 3, 2026Logan Ritchie, Sushant Mehta, Liudas Panavas +1Software Engineering Agents Cross-Domain Transfer Learning
Surge AI
AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving
Aug 1, 2026Hao Mark Chen, Jinnan Guo, Wayne Luk +1LLM Inference Acceleration Long-Horizon Agent Tasks
Imperial College London, UK
From Failures to Supervision: DynamicEnvPlan for Robust Long-Horizon Embodied Planning
Aug 1, 2026Hao Yuan, Yuxin Wang, Lei Ji +1Robot Failure Recovery Robot Task Planning
University of Chinese Academy of Sciences · †Independent researchers. · 3Beijing Academy of Artificial Intelligence (BAAI)
Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
Jul 29, 2026Xu Zheng, Zhuomin Chen, Chaohao Lin +4Long-Horizon Agent Tasks Long-Horizon LLM Agents
1Florida International University, Miami, FL, USA · 2Arizona State University, Tempe, AZ, USA · 3NEC Laboratories America, Princeton, NJ, USA +1
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Jul 29, 2026Jingbo Zhou, Yusai Zhao, Qi Bao +12Computer-Use Agent Benchmarks Computer-Use Agents
Agent Frontier Team, Large Model Frontier Research Department, Baidu Inc., China.
AgentGUI: An Interface for Observing and Steering Long-Running AI Agents
Jul 28, 2026Xuan Zhao, Jiwoong Sohn, Qinyue Zheng +1GUI Agents Human-in-the-Loop AI
ETH Zürich · ETH AI Center
ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning
Jul 28, 2026Jiaqi Zhang, Tong Chen, Junliang Yu +2Group Relative Policy Optimization Agentic Reasoning
The University of Queensland · Griffith University
Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering
Jul 27, 2026Rushi Qiang, Changhao Li, Haotian Sun +3LLM Agent Orchestration LLM Agents
Georgia Institute of Technology
ACM: Agentic Context Management for Long Horizon Tasks
Jul 26, 2026Xiaochuan Li, Ryan Ming, Meng Chu +3LLM Agent Training Long-Horizon Agent Tasks
Carnegie Mellon University · Meta
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Jul 24, 2026Yan Yang, Xiangru Jian, Ziyang Luo +7Computer-Use Agents Tool-Using Agents
Salesforce AI Research
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
Jul 23, 2026Jiabin Lou, Haopeng Wang, Yuanshuai Wang +6Embodied Navigation Robot Navigation
Beihang University, Beijing 100191, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou 311115, China
Offline RL with Hierarchical Action Chunking
Jul 23, 2026Ahad JawaidHierarchical RL Offline RL
The University of Texas at Dallas
PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
Jul 22, 2026Alexis Fox, Junlin Wang, Paul Rosu +1Persistent Memory for Language Models Long-Horizon Agent Tasks
Duke University
Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
Jul 22, 2026Kaibing Yang, Guangfeng Cai, Shengtian Yang +6Group Relative Policy Optimization RL Exploration
Southeast University · Kuaishou Technology · Work done during an internship at Kuaishou Technology, supervised by Jun Xu. +1
SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis
Jul 20, 2026Zhuohang Fan, Beichen Zhang, Yuanfa Li +4Trajectory Generation Synthetic Data Generation
Harbin Institute of Technology, Weihai, China · Harbin Institute of Technology (Weihai) Qingdao Research Institute, Qingdao, China
Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents
Jul 17, 2026Zedong Yu, Qianxing Li, Zhi Gao +8Computer-Use Agent Benchmarks GUI Agents
Beijing University of Posts and Telecommunications, Beijing, China · State Key Laboratory for General Artificial Intelligence, BIGAI, Beijing, China · China University of Geosciences (Beijing), Beijing, China +1
ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning
Jul 17, 2026Shuaiyu Zhou, Fengpeng Yue, Zengjie Hu +5Tool-Use Evaluation Agentic RL
LongCat Interaction Team, Meituan, Beijing, China · Peking University, Beijing, China · Fudan University, Shanghai, China +1
Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics
Jul 14, 2026Yue Chang, Rufeng Chen, Yifan Tian +73D SGG Long-Horizon Agent Tasks
1The Hong Kong University of Science and Technology (Guangzhou) · 2Jilin University
A Glimpse into Long-term Physical Coexistence with Intelligent Robots
Jul 13, 2026Weiqi Jin, Peijun Tang, Kuncheng Luo +5Multi-Robot Systems Assistive Robotics
Astribot Team

Aug 8, 2026, cs.AIJ/K move · Enter open · S save

SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning

Keyang Zhong, Kuo Wang, Peng Liu, Quanlong Zheng+4

Sun Yat-sen University · Shenzhen Loop Area Institute · Guangdong OPPO Mobile Telecommunications Corp., Ltd.+2

Temporal Video Grounding Group Relative Policy Optimization Egocentric Video Understanding Video Reasoning Long-Horizon Agent Tasks RL for Tool Use

Open paper AskPDF arXiv

Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multimodal models with limited context and the grounding of key video segments. While Chain-of-Tool-Thought (CoTT) agent systems enable iterative retrieval and inspection, they suffer from error propagation due to rigid zoom-in strategies that lack recovery mechanisms. In this work, we address these challenges through SCOUT (Self-Checking Chain-Of-Tool-thought), a recovery-aware agentic framework introducing an adaptive policy that evaluates intermediate tool observations and dynamically trades off exploitation (zoom-in) and exploration (region switching), enabling robust multi-hop reasoning over extremely long horizons. However, training such multi-turn tool-using agents remains challenging, as existing RL methods rely on sparse outcome-level rewards and lack supervision over extended decision trajectories, resulting in suboptimal credit assignment for long-horizon reasoning. To address this, we develop UPS-GRPO, an uncertainty-prioritized policy optimization method that concentrates exploration on high-uncertainty post-tool states while preserving sample efficiency. We further introduce a turn-level advantage decomposition that integrates outcome rewards with tool-grounded temporal alignment rewards for improved credit assignment. Experiments show that SCOUT achieves state-of-the-art results on ultra-long egocentric benchmarks, while remaining competitive on shorter-horizon long-video settings.

Momentum

Related topics

Latest papers 127