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 →

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
May 11, 2026Lingjun Zhang, Changjie Wu, Linzhe Shi +6Autonomous Driving Large Vision Language Models
Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators
May 11, 2026Xiaoxiao Lu, Ye Yuan, Jiahao ShiNeural Partial Differential Equation Solvers Long-Horizon Forecasting
Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
May 10, 2026Kewei Chen, Yayu Long, Mingsheng ShangIterative Reinforcement Learning Long-Horizon Planning
QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking
May 10, 2026Mayank Anand, Mohammad Saqlain, Kyan Mahajan +3Large Inter-Frame Displacements Spatiotemporal Representations
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
May 9, 2026Giridhar Ganapavarapu, Dhaval PatelModel Context Protocol Long-Horizon
ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
May 9, 2026Yanbin Hu, Jin Cui, Jiayi Lu +6Vision-Language-Action Models Long-Horizon Planning
Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
May 9, 2026Zhuofu Chen, Rui Pan, Yinwei Dai +1Compaction Long-Horizon Agents
Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
May 8, 2026Anmol Gulati, Hariom Gupta, Elias Lumer +2Long-Horizon Agents Injecting
BrickCraft: Visuomotor Skill Composition with Situated Manual Guidance for Long-Horizon Interlocking Brick Assembly
May 8, 2026Jichuan Yu, Bowei Li, Zhenran Tang +4Building Blocks Visuomotor Control
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
May 8, 2026Jiaqi Shao, Yiyi Lu, Yunzhen Zhang +1Agent Memory Agentic Evaluations
Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
May 8, 2026Jiaxuan Gao, Yongjian Guo, Zhong Guan +5Vision-Language-Action Models World Models
MedHorizon: Towards Long-context Medical Video Understanding in the Wild
May 7, 2026Bodong Du, Bowen Liu, Yang Yu +8Medical Visual Question Answering Video Understanding
Stop Comparing LLM Agents Without Disclosing the Harness
May 7, 2026Yunbei Zhang, Janet Wang, Yingqiang Ge +3Agent Harness Large Language Model Agents
SEQUOR: A Multi-Turn Benchmark for Realistic Constraint Following
May 7, 2026Beatriz Canaverde, Duarte M. Alves, José Pombal +2Multi-Turn Conversations Instruction
When to Trust Imagination: Adaptive Action Execution for World Action Models
May 7, 2026Rui Wang, Yue Zhang, Jiehong Lin +4Efficient World-Action Model Executable Robot Behavior
Milestone-Guided Policy Learning for Long-Horizon Language Agents
May 7, 2026Zixuan Wang, Yuchen Yan, Hongxing Li +7Long-Horizon Agents Agentic Reinforcement-Learning Framework
MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware
May 7, 2026Senthil Palanisamy, Abhishek Anand, Satpal Singh Rathore +3Egocentric Dataset Scalable Robot Data Synthesis
ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
May 7, 2026Fan HuangLarge Language Model Reasoning Reflections
Agentic Coding Needs Proactivity, Not Just Autonomy
May 7, 2026Nghi D. Q. Bui, Georgios EvangelopoulosCoding Agents Proactive
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
May 6, 2026Yijun Lu, Rui Ye, Yuwen Du +3Long-Horizon Agents Agent Memory
Tree-based Credit Assignment for Multi-Agent Memory System
May 6, 2026Marina Mao, Alexandr Liu, Pengbo Li +3Agent Memory Credit Assignment
ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
May 6, 2026Yurui Du, Pinhao Song, Yutong Hu +1Long-Horizon Planning Deepmind Control Suite
HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks
May 6, 2026Nandiraju Gireesh, Yuanliang Ju, Chaoyi Xu +3Diffusion Planning Classical Planning
Pro $^2$ Assist: Continuous Step-Aware Proactive Assistance with Multimodal Egocentric Perception for Long-Horizon Procedural Tasks
May 5, 2026Lilin Xu, Bufang Yang, Siyang Jiang +6Multimodal Agents Artificial Intelligence Assistants
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems
May 5, 2026Jie Zhou, Qin Chen, Liang HeObjectives Multi-Objective Optimization
MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
May 5, 2026Jiayi Chen, Yingcong Li, Guiling WangLarge Language Model Agents Large Language Model Baselines
Refining Compositional Diffusion for Reliable Long-Horizon Planning
May 4, 2026Kyowoon Lee, Yunhao Luo, Anh Tong +1Diffusion Planning Long-Horizon Planning
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
May 4, 2026Ruofeng Yang, Yongcan Li, Shuai LiAutoresearch Adversarial Evaluation
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
May 4, 2026Sunghwan Kim, Junhee Cho, Beong-woo Kwak +6Long-Horizon Tasks Large Models
The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents
May 4, 2026Yelin KimSoftware Engineering Long-Horizon Agents
Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
May 4, 2026Wenyi Wu, Sibo Zhu, Kun Zhou +1Long-Horizon Agents Long-Horizon Planning
Moira: Language-driven Hierarchical Reinforcement Learning for Pair Trading
May 3, 2026Polydoros Giannouris, Yuechen Jiang, Lingfei Qian +5Hierarchical Reinforcement Learning Sequential Decision Making
TRAP: Tail-aware Ranking Attack for World-Model Planning
May 3, 2026Siyuan Duan, Ke Zhang, Xizhao LuoBackdoor Attacks Classical Planning
Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
May 3, 2026Zhilong Zhang, Wenyu Luo, Haonan Wang +9Flow-Matching Vision-Language-Action Long-Horizon Planning
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
May 2, 2026Jie-Jing Shao, Haiyan Yin, Yueming Lyu +5Long-Horizon Agents Neuro-Symbolic Framework
Online Safety Filter for Deformable Object Manipulation with Horizon Agnostic Neural Operators
May 1, 2026Jiaxing Li, Hanjiang Hu, Zhuoyuan Wang +2Safety Filters Safety Constraints
Beyond Compaction: Structured Context Eviction for Long-Horizon Agents
May 1, 2026Andrew Semenov, Svyatoslav DorofeevLong-Horizon Agents Local Windows
Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
May 1, 2026Jinkun Liu, Haohan Chi, Lingfeng Zhang +6Long-Horizon Planning Visual Reasoning
AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?
May 1, 2026Ranit Karmakar, Jayita ChatterjeeFrontier Models Agent Framework
RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects
Apr 30, 2026Tim Missal, Lucas Domingues, Berk Guler +3Deformable Objects Latent Dynamics
KellyBench: A Benchmark for Long-Horizon Sequential Decision Making
Apr 30, 2026Thomas Grady, Kip Parker, Iliyan Zarov +3Sequential Decision Making Sequential
Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents
Apr 30, 2026Chunhui Zhang, Yuxuan Wang, Aoyang Qin +4Embodied Agents Classical Planning
Walk With Me: Long-Horizon Social Navigation for Human-Centric Outdoor Assistance
Apr 29, 2026Lingfeng Zhang, Xiaoshuai Hao, Xizhou Bu +11Long-Horizon Planning Flow-Matching Vision-Language-Action
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
Apr 29, 2026Jinze Li, Yang Zhang, Xin Yang +5Agent Memory Long-Horizon Agents
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
Apr 29, 2026Tianyu Liu, Yuhao Shen, Xinyi Hu +8Speculative Decoding Kv-Cache Blocks
ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents
Apr 28, 2026Zhou Hanlin, Chan Huah YongLong-Horizon Tasks Multi-Agent Orchestration Frameworks
Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
Apr 27, 2026Lawrence Keunho Jang, Jing Yu Koh, Daniel Fried +1Long-Horizon Tasks Web Agents
DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute
Apr 26, 2026Nishant Balepur, Malachi Hamada, Varsha Kishore +9Long-Horizon Agents Feedback Learning
Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue
Apr 25, 2026Yangyang Zhao, Linfan Dai, Li Cai +2Long-Horizon Tasks Label Constraint Modeling
Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
Apr 24, 2026Ziyao Wang, Bingying Wang, Hanrong Zhang +7Vision-Language-Action Models Robotic Datasets
SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
Apr 24, 2026Jichao Wang, Liuyang Bian, Yufeng Zhou +9Long-Horizon
CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Models
Apr 24, 2026Khoa Vo, Sieu Tran, Taisei Hanyu +8Long-Horizon Planning Generalizable Robotic Manipulations
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
Apr 23, 2026Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel +3Agent Memory Long-Term Memory
Long-Horizon Manipulation via Trace-Conditioned VLA Planning
Apr 23, 2026Isabella Liu, An-Chieh Cheng, Rui Yan +7Long-Horizon Planning Flow-Matching Vision-Language-Action
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
Apr 23, 2026Buqiang Xu, Yijun Chen, Jizhan Fang +5Long-Horizon Consolidation
How VLAs (Really) Work In Open-World Environments
Apr 23, 2026Amir Rasouli, Yangzheng Wu, Zhiyuan Li +4Vision-Language-Action Models Robotics
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
Apr 22, 2026Xiyang Wu, Zongxia Li, Guangyao Shi +5Skill Evolution Agent Skill Ecosystems
ALAS: Adaptive Long-Horizon Action Synthesis via Async-pathway Stream Disentanglement
Apr 22, 2026Yutong Shen, Hangxu Liu, Lei Zhang +4Hierarchical Reinforcement Learning Motor Skills
Cortex 2.0: Grounding World Models in Real-World Industrial Deployment
Apr 22, 2026Adriana Aida, Walid Amer, Katarina Bankovic +25Generalizable Robotic Manipulations Long-Horizon Planning
From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
Apr 21, 2026Md Nayem Uddin, Kumar Shubham, Eduardo Blanco +2Agent Memory Long-Term Memory

May 11, 2026 · cs.CVJ/K move · Enter open · S save

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving

Lingjun Zhang, Changjie Wu, Linzhe Shi, Jiangyang Li+5

End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual reasoning to enhance the robustness and accuracy of driving decisions. However, the reasoning mechanisms employed in most methods are direct adaptations from general domains, lacking in-depth exploration tailored to autonomous driving scenarios, particularly within visual reasoning modules. In this paper, we propose a driving world model that performs parallel prediction of latent semantic features for consecutive future frames in the bird's-eye-view (BEV) space, thereby enabling long-horizon modeling of future world states. We also introduce an efficient and adaptive text reasoning mechanism that utilizes additional social knowledge and reasoning capabilities to further improve driving performance in challenging long-tail scenarios. We present a novel, efficient, and effective approach that achieves state-of-the-art (SOTA) results on the closed-loop Bench2drive benchmark. Codes are available at: https://github.com/hotdogcheesewhite/DeepSight.

Autonomous Driving Large Vision Language Models Visual Reasoning Long-Horizon

Open paper Ask about it PDF