From Failures to Supervision: DynamicEnvPlan for Robust Long-Horizon Embodied Planning

• URL: http://arxiv.org/abs/2608.00613v1
• Date: Sat, 01 Aug 2026 12:09:47 GMT
• Title: From Failures to Supervision: DynamicEnvPlan for Robust Long-Horizon Embodied Planning
• Abstract summary: We introduce DynamicEnvPlan, a closed-loop framework for high-level planning in dynamic environments.<n>It extends embodied task execution with humanoid agents, high-level primitive skills, structured semantic memory, and controllable perturbations.<n>The resulting traces are used for staged supervised fine-tuning, enabling the planner to learn from both nominal execution and recovery trajectories.
• Score: 11.738655774128366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physical-world interaction is inherently dynamic, as environments can evolve during execution, requiring agents to adapt their plans under non-stationary conditions. We study this challenge through long-horizon embodied planning under environment deviations and execution uncertainty. Existing embodied-task benchmarks can expose such failures, but these failures are usually treated as evaluation outcomes instead of learnable signals for training agents to recover. In this work, we introduce DynamicEnvPlan, a closed-loop framework for high-level planning in dynamic environments. It extends embodied task execution with humanoid agents, high-level primitive skills, structured semantic memory, and controllable perturbations. Our data synthesis design consists of planning, perturbation, and guarded correction modules that turn dynamic execution states into recovery-oriented traces. The resulting traces are used for staged supervised fine-tuning, enabling the planner to learn from both nominal execution and perturbed recovery trajectories. Using 104 task-scene combinations spanning i.i.d., compositional generalization, and out-of-distribution settings for fine-tuning and evaluation, DynamicEnvPlan boosts success rate from 33.3% for the base planner to 76.2%, while improving across all seven evaluation metrics critical to physical-world interaction, including safety and affordance compliance.

Related papers

• Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning [60.888463449435484]
  We present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift.<n>We show that imitation learning methods achieve high scores in ID benchmarks, but suffer from persistent drift when subjected to temporally correlated actuation noise.<n>Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.
  arXiv  Detail & Related papers  (2026-07-08T18:23:48Z)
• Occluding the Solution Space: Planner-Agnostic Adversarial Attacks on Tolerance-Aware Manipulation [57.9825059129472]
  We propose a planner-agnostic attack framework for tolerance-aware manipulation.<n>Our approach shifts the evaluation paradigm to task-level feasibility over goal regions.<n>Online, we formulate the attack as a budgeted maximum-coverage optimization.
  arXiv  Detail & Related papers  (2026-07-04T08:14:44Z)
• ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control [54.267632784131415]
  ReactiveBFM is a real-time-loop planning-control framework for humanoids.<n>It mitigates fatal cumulative exposure bias via a scheduled prefix sampling curriculum.<n>It demonstrates unprecedented physical agility across a vast repertoire of text-conditioned closed-loop motions.
  arXiv  Detail & Related papers  (2026-06-29T14:27:27Z)
• Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints [12.864903019173106]
  Recent neuro-symbolic methods improve planning efficiency by learning object-importance scores to prune task-irrelevant objects.<n>We introduce a 3R strategy into the lower-level planning, using parallel Repair, Restart, and Rollback recovery to provide reliable and adaptive feedback for upper-level learning.<n>Experiments on three challenging benchmarks demonstrate state-of-the-art performance, including an 80.04% reduction in failure rate and a 57.14% reduction in planning time.
  arXiv  Detail & Related papers  (2026-06-05T03:44:48Z)
• RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following [39.9780803736704]
  Embodied instruction following (EIF) requires agents to understand and execute complex natural language commands within interactive 3D environments.<n>We introduce RePlan-Bot, a novel EIF agent that performs multi-level, continuous replanning throughout task execution.
  arXiv  Detail & Related papers  (2026-05-25T13:44:18Z)
• PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement [22.285969725581044]
  Large language model (LLM)-based agents generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons.<n>PIVOT addresses this plan-execution misalignment through a self-supervised framework that treats trajectories as optimizable objects iteratively refined via environment interaction.
  arXiv  Detail & Related papers  (2026-05-11T20:43:20Z)
• ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation [10.278758849939917]
  We present ANCHOR, a closed-loop framework that aligns symbolic reasoning with verifiable physical state during execution.<n>ANCHOR improves task success from 53.3% to 71.7% and achieves a 71.4% recovery rate under perturbations.
  arXiv  Detail & Related papers  (2026-04-28T07:37:39Z)
• Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems [54.887871365121775]
  Multi-robot control in cluttered environments is a challenging problem that involves complex physical constraints.<n>We propose a hybrid multi-robot control framework that jointly optimize task and motion planning.<n>Our approach consistently improves task success over motion-agnostic and VLA-based baselines.
  arXiv  Detail & Related papers  (2026-04-22T22:58:47Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance [11.621973074884002]
  HiPlan is a hierarchical planning framework for large language model (LLM)-based agents.<n>It decomposes complex tasks into milestone action guides for general direction and step-wise hints for detailed actions.<n>In the offline phase, we construct a milestone library from expert demonstrations, enabling structured experience reuse.<n>In the execution phase, trajectory segments from past milestones are dynamically adapted to generate step-wise hints.
  arXiv  Detail & Related papers  (2025-08-26T14:37:48Z)
• Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach [82.27842884709378]
  We propose a framework that prioritizes natural language understanding and structured reasoning to enhance the agent's global understanding of the environment.<n>Our method outperforms previous approaches, particularly achieving a 44.4% relative improvement in task success rate.
  arXiv  Detail & Related papers  (2025-05-22T09:08:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.