Preprint
World models
Unknown
This paper introduces world models, enabling agents to learn and plan in latent spaces, leading to the Dreamer series for long-horizon reinforcement learning.
0Reinforcement Learning
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
12 papersPreprint2014
Collaborative foresight: Complementing long-horizon strategic planning
Unknown
An action case study demonstrates effective integration of collaborative planning with long-range foresight in a hierarchical government research organization.
0Jan 1, 2014
Preprint2026
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Jiayu Liu, Qihan Lin, Cheng Qian, et al.
Evaluates LLM tool-use agents on long-horizon planning in large-scale tool ecosystems, finding most models below two-thirds accuracy.
0Jan 1, 2026
arXiv
Preprint2026
Instructflow: Adaptive symbolic constraint-guided code generation for long-horizon planning
Unknown
Instructflow uses adaptive symbolic constraints to guide code generation for long-horizon robotic planning.
0Jan 1, 2026Code Generation
Preprint2024
Learning for long-horizon planning via neuro-symbolic abductive imitation
Jiejing Shao, Haoran Hao, Xiaowen Yang, et al.
This paper introduces a neuro-symbolic abductive imitation learning framework for long-horizon planning.
0Nov 1, 2024Reasoning
arXiv
Preprint2025
Instruction-augmented long-horizon planning: Embedding grounding mechanisms in embodied mobile manipulation
Unknown
IALP system integrates grounding mechanisms into long-horizon planning for embodied mobile manipulation.
0Jan 1, 2025Instruction Tuning
Preprint2024
Long-horizon planning for multi-agent robots in partially observable environments
Unknown
This paper uses language models to enable long-horizon planning for multi-agent robots in partially observable environments, overcoming traditional RL and HRL limitations.
0Jan 1, 2024
Preprint2024
Planning transformer: Long-horizon offline reinforcement learning with planning tokens
Joseph Clinton, Robert Lieck
Planning Transformer introduces planning tokens for dual time-scale prediction to enable long-horizon offline reinforcement learning with implicit planning.
0Sep 1, 2024TransformersReinforcement Learning
arXiv
Preprint2010
Broadly-exploring, local-policy trees for long-horizon task planning
Brian Ichter, Pierre Sermanet, Corey Lynch
This paper introduces a tree-based planning method that combines broad exploration with local policy reuse for long-horizon tasks in high-dimensional state spaces.
0Jan 1, 2010
arXiv
Preprint2020
Long-horizon visual planning with goal-conditioned hierarchical predictors
Unknown
This paper introduces a hierarchical prediction model for long-horizon visual planning using coarse-to-fine goal-conditioned predictors.
0Jan 1, 2020
Preprint2025
Plan-and-act: Improving planning of agents for long-horizon tasks
Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, et al.
PLAN-AND-ACT improves long-horizon planning for agents by integrating plan generation with execution, achieving 57.58% success on WebArena-Lite.
0Jan 1, 2025
arXiv
PreprintarXiv.org2026
Demystifying reinforcement learning for long-horizon tool-using agents: A comprehensive recipe
Xixi Wu, Qianguo Sun, Ruiyang Zhang, et al.
A systematic empirical study demystifying the RL design space for long-horizon, tool-using agents using TravelPlanner as a testbed.
3Jan 1, 2026Reinforcement Learning
arXiv