Long-Horizon Tasks

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

27 new papers

A weekly snapshot of new work published in Long-Horizon Tasks.

Period ending 2026-09-14

9 new papers

A weekly snapshot of new work published in Long-Horizon Tasks.

Inside this field

Focused directions

Focused topic

Long-Horizon Agents

Within Long-Horizon Tasks

152 papersExplore

Focused topic

Long-Horizon Planning

Within Long-Horizon Tasks

148 papersExplore

Focused topic

Long-Horizon Tasks

Within Long-Horizon Tasks

125 papersExplore

Focused topic

Long-Horizon

Within Long-Horizon Tasks

118 papersExplore

Focused topic

Horizon

Within Long-Horizon Tasks

45 papersExplore

514 papers

Latest in Long-Horizon Tasks

Browse all topics →

ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
May 26, 2026Zihang Cheng, Duanchu Wang, Cheng Li +3Canopy Ecosystems
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
May 26, 2026Yipeng Ouyang, Xin Huang, Bingjie Liu +3Long-Horizon Agents Workflow Automation and Optimization
Anchor: Mitigating Artifact Drift in Agent Benchmark Generation
May 25, 2026Maksim Ivanov, Abhijay RanaArtificial Intelligence Agents Workflow Generation
Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory
May 25, 2026Abdelghny Orogat, Essam MansourAgent Memory Long-Term Memory
Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning
May 25, 2026Hyungkyu Kang, Byeongchan Kim, Min-hwan OhGoal-Conditioned Reinforcement Learning Goal-Conditioned Policy
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
May 25, 2026Yeonjun In, Wonjoong Kim, Sangwu Park +2Interaction History Personalization
Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents
May 23, 2026Yuxin Zhang, Mengxue Hu, Zheng Lin +8Long-Horizon Tasks Cloud
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
May 23, 2026Yuyang Hu, Hongjin Qian, Shuting Wang +5Long-Horizon Agents Long-Horizon Tasks
SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
May 23, 2026Yuyang Hu, Hongjin Qian, Shuting Wang +5Long-Horizon Agents Agent Memory
An Interactive Paradigm for Deep Research
May 22, 2026Lin Ai, Victor S. Bursztyn, Xiang Chen +2Deep Research Long-Horizon Tasks
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
May 22, 2026Jian Xie, Tianhe Lin, Zilu Wang +16Deep Research Task Synthesis
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
May 22, 2026Chong Cheng, Peilin Tao, Nanjie Yao +93D Reconstruction Non-Rigid Shape Matching
Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents
May 22, 2026Yuandao Cai, Yuzhang Zhu, Liyou Gao +2Long-Horizon Agents Objectives
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
May 21, 2026Daewon Choi, Kyunghyun Park, Woomin Song +4Large Language Model Agents Long-Horizon Tasks
SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?
May 20, 2026Kevin Han, Renfei Zhang, Kathy Wei +3Drug Design Drug Discovery
DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation
May 20, 2026Sixiong Xie, Zhuofan Shi, Haiyang Shen +8Deep Research Long-Horizon
Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
May 19, 2026Matthew Bendel, Stephen W. Bailey, Mithilesh Vaidya +2Autoregressive Video Generation Video Quality
Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
May 19, 2026Wenjie Tang, Minne Li, Sijie Huang +2Reinforcement Learning With Verifiable Reward Credit Assignment
CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation
May 19, 2026Xinyuan Luo, Xingrui Chen, Xunjian Yin +6Humanoid Loco-Manipulation End-Effector Pose
Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction
May 19, 2026Xia Jiang, Yaoxin Wu, Yew-Soon Ong +1Long-Horizon Planning Foresight
World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks
May 19, 2026Zuyao Lin, Jianhui Zhang, Peidong Jia +3World Models Long-Horizon Planning
Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
May 19, 2026Yang Fu, Haomin Bao, Rohit Sonker +4Plasma Shape Control Joint Reinforcement Learning
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
May 18, 2026Yuxuan Gao, Megan Wang, Yi Ling Yu +2Delegation Agent Decisions
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
May 18, 2026Ziyun Zeng, Hang Hua, Bocheng Zou +3Agent Memory Graphical User Interface
SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
May 18, 2026Wencan Jiang, Jiangning Zhang, Jianbiao Mei +6Agentic Control Reactive
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
May 18, 2026Hyunji Lee, Justin Chih-Yao Chen, Joykirat Singh +3Agent Memory Long-Horizon Tasks
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
May 18, 2026Woongyeng Yeo, Yumin Choi, Taekyung Ki +1Long-Horizon Agents Hindsight
Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents
May 17, 2026Nikola MilosevicLarge Language Model Memory Episodic Experiences
Scale-Equivariant Generative Forecasting: Weight-Tied Dilated Convolutions, Wavelet Scattering Inputs, and Spectral-Consistency Training for Self-Similar Time Series
May 17, 2026Andrea MorandiDiscrete Wavelet Transform Exact Equivariance
Visual Sculpting: Visually-Aligned Planning Representations for Long-Horizon Robot Clay Sculpting
May 17, 2026Peter Schaldenbrand, Jean OhDeformable Objects Long-Horizon Planning
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
May 17, 2026Qingnan Ren, Shun Zou, Shiting Huang +11Coding Agents Software
PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
May 16, 2026Sikuan Yan, Sicheng Dong, Haotong Wang +8Multimodal Memory Video Understanding
BAT-Nav: Belief-Based Arbitration and Termination via Remaining Discoverability in Multi-Goal Semantic Navigation
May 16, 2026Xi Lin, Kangyi Wu, Jiayi Li +3Object Goal Navigation Long-Horizon Planning
Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning
May 16, 2026Yaniv Hassidof, Adir Morgan, Yilun Du +1Diffusion Planning Long-Horizon Planning
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
May 15, 2026Haolin Chen, Deon Metelski, Leon Qi +30Healthcare Artificial Intelligence Agents
Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning
May 15, 2026Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen +1Long-Horizon Planning Imitation Learning
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
May 15, 2026Xinbo Xu, Ruihan Yang, Haiyang Shen +13Agentic Benchmarks Roadmap
GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks
May 15, 2026Davide Buoso, Andrea Protopapa, Stefano Di Carlo +2Visuomotor Policy Imitation Learning
Learn2Splat: Extending the Horizon of Learned 3DGS Optimization
May 15, 2026Naama Pearl, Stefano Esposito, Haofei Xu +63D Gaussian Splats Novel View Synthesis
Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human Feedback
May 15, 2026Pengcheng Dai, He Wang, Dongming Wang +2Multi-Agent Reinforcement Learning Reinforcement Learning From Human Feedback
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
May 14, 2026Suyoung Bae, Jaehoon Lee, Changkyu Choi +2Repository-Level Code Understanding Documentation
When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution
May 14, 2026Zilin Zhu, Longteng Guo, Yanghong Mei +5Long-Horizon Planning Embodied Agents
ASH: Agents that Self-Hone via Embodied Learning
May 14, 2026Benjamin Schneider, Xavier Schneider, Victor Zhong +1Long-Horizon Agents Embodied Agents
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
May 13, 2026Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang +2Agentic Benchmarks Large Language Model Agents
McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting
May 13, 2026Penghui Wen, Yu Luo, Lintao Wang +4Precipitation Long-Horizon Forecasting
Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models
May 13, 2026Zixing Lei, Changxing Liu, Yichen Xiong +5Vision-Language-Action Models Executable Robot Behavior
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
May 13, 2026Yuxin Liu, Ziang Ye, Yueqing Sun +6Cognitive Map Long-Horizon Agents
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
May 12, 2026Di Wu, Zixiang Ji, Asmi Kawatkar +4Agent Memory Long-Horizon Agents
Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
May 12, 2026Hari K. Prakash, Charles H MartinOverfitting Neural Network
Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
May 12, 2026Yunbei Xu, Yuzhe Yuan, Ruohan ZhanKullback-Leibler Divergence Autoregressive Model
PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents
May 12, 2026Jingyi Peng, Zhongwei Wan, Weiting Liu +1Long-Horizon Tasks Prism
VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
May 12, 2026Chenhao Qiu, Yechao Zhang, Xin Luo +2Agentic Video Generation Video Question Answering
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
May 12, 2026Yihao Wang, Haoran Xu, Renjie Gu +10Agent Memory Long-Horizon Agents
HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
May 12, 2026Conglang Zhang, Yifan Zhan, Qingjie Wang +10Autonomous Driving Simulation Autoregressive Rollout
Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
May 12, 2026Shengjie Wang, Guanghe Li, Zonghan Yang +1Hindsight Long-Horizon Tasks
The DAWN of World-Action Interactive Models
May 12, 2026Hongbo Lu, Liang Yao, Chenghao He +6Efficient World-Action Model World Models
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
May 12, 2026Joykirat Singh, Zaid Khan, Archiki Prasad +5Long-Horizon Agents Initial Human Belief Distributions
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
May 11, 2026Shuangrui Ding, Xuanlang Dai, Long Xing +14Agentic Benchmarks Agentic Evaluations
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
May 11, 2026Mingxi Zou, Zhihan Guo, Langzhang Liang +6Agent Memory Long-Horizon Agents
The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
May 11, 2026Xinrun Wang, Chang Yang, He Zhao +2Long-Horizon Tasks Engineering

May 26, 2026 · cs.CVJ/K move · Enter open · S save

ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes

Zihang Cheng, Duanchu Wang, Cheng Li, Jing Huang+2

Xi’an Jiaotong University · Xidian University · Zhejiang University

Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological analysis involves multi-step filtering, numerical aggregation, neighborhood reasoning, and verifiable evidence. We introduce ForestHG-Trace, a framework for traceable long-horizon ecological reasoning over forest environments. It represents multimodal NEON forest scenes as ecological hypergraphs, where tree instances, spatial units, semantic groups, and neighborhood relations support higher-order reasoning beyond pairwise scene graphs. An LLM-guided agent then invokes deterministic tools for reading, filtering, expansion, aggregation, comparison, and auditing, producing replayable execution traces and compact evidence records rather than only free-form answers. We further construct ForestTraceQA, an executable benchmark for evaluating ecological QA across diverse task types and reasoning depths. Experiments show that ForestHG-Trace substantially improves answer accuracy and execution faithfulness over single-step baselines and scene-graph agents, while highlighting execution depth as the main bottleneck for long-horizon ecological QA.

Canopy Ecosystems Long-Horizon

Open paper Ask about it PDF