CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks

• URL: http://arxiv.org/abs/2505.07261v3
• Date: Sun, 12 Oct 2025 04:52:00 GMT
• Title: CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks
• Abstract summary: Diffusion-based planners have shown strong performance in short-horizon tasks but often fail in complex, long-horizon settings.<n>We propose Coupled Hierarchical Diffusion, a framework that models HL sub-goals and LL trajectories jointly within a unified diffusion process.<n> Experiments across maze navigation, tabletop manipulation, and household environments show that CHD consistently outperforms both flat and hierarchical diffusion baselines.
• Score: 10.13048343565914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based planners have shown strong performance in short-horizon tasks but often fail in complex, long-horizon settings. We trace the failure to loose coupling between high-level (HL) sub-goal selection and low-level (LL) trajectory generation, which leads to incoherent plans and degraded performance. We propose Coupled Hierarchical Diffusion (CHD), a framework that models HL sub-goals and LL trajectories jointly within a unified diffusion process. A shared classifier passes LL feedback upstream so that sub-goals self-correct while sampling proceeds. This tight HL-LL coupling improves trajectory coherence and enables scalable long-horizon diffusion planning. Experiments across maze navigation, tabletop manipulation, and household environments show that CHD consistently outperforms both flat and hierarchical diffusion baselines. Our website is: https://sites.google.com/view/chd2025/home

Related papers

• Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations [53.931465193216155]
  We introduce Hindsight Supervised Learning (HSL), where an auxiliary LLM reviews each completed trajectory and relabels it with all of the natural-language goals the agent actually achieved.<n>HSL pairs the trajectory with its relabeled goals and uses these pairs for additional fine-tuning.<n>Our experiments show that HSL is flexible and compatible with existing post-training pipelines.
  arXiv  Detail & Related papers  (2026-07-05T11:21:26Z)
• TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL [72.7712729541565]
  Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context.<n>A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions.<n>We address these challenges with TempAct, a planner--executor reinforcement learning framework that jointly optimize temporal decomposition and step-conditioned execution for temporally plausible AR video generation.
  arXiv  Detail & Related papers  (2026-06-26T12:19:28Z)
• HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning [51.95194664412812]
  Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks.<n>We propose Hierarchical Planning and Information Folding (HIPIF) for long-horizon LLM agent learning.<n>HIPIF trains the agent end-to-end to organize long-horizon execution around explicit subgoals while folding completed subgoal histories to reduce long-context interference.
  arXiv  Detail & Related papers  (2026-06-09T07:35:14Z)
• Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning [44.52185127499181]
  Compositional diffusion models offer a promising route to long-horizon planning.<n>But enforcing local behavior over long chains is often insufficient for a coherent global structure to emerge.<n>Recent works tackle this limitation through intrinsic search, which explores multiple paths during the denoising process.
  arXiv  Detail & Related papers  (2026-05-16T07:53:04Z)
• HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks [11.988273046923782]
  We introduce Hierarchical Diffusion-Flow (HDFlow), a novel hierarchical planning framework.<n>HDFlow optimally leverages the strengths of diffusion and rectified flow models to overcome the limitations of single-paradigm generative planners.<n>We evaluate HDFlow on four challenging furniture assembly tasks in both simulation and real-world, where it significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-06T06:08:51Z)
• Refining Compositional Diffusion for Reliable Long-Horizon Planning [31.40044829548484]
  We propose a training-free guidance method that steers compositional sampling toward high-density, globally coherent plans.<n> Experiments on challenging long-horizon tasks from OGBench, including locomotion, object manipulation, and pixel-based observations, demonstrate that RCD consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2026-05-04T18:44:19Z)
• The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break [69.91172974854422]
  HORIZON is a cross-domain diagnostic benchmark for analyzing long-horizon failure behaviors in large language model (LLM) agents.<n>We evaluate state-of-the-art (SOTA) agents from multiple model families to study horizon-dependent degradation patterns.<n>Our findings offer an initial methodological step toward systematic, cross-domain analysis of long-horizon agent failures.
  arXiv  Detail & Related papers  (2026-04-13T19:11:42Z)
• Mode Seeking meets Mean Seeking for Fast Long Video Generation [79.62764340469]
  Scaling video generation from seconds to minutes faces a critical bottleneck.<n>We propose a training paradigm where Mode Seeking meets Mean Seeking.<n>Our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency.
  arXiv  Detail & Related papers  (2026-02-27T18:59:02Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation [36.30669615593167]
  We argue that Euclidean-based Flow Matching overlooks fundamental limitations of flat geometry.<n>We propose path-decoupled Hyperbolic Flow Matching, leveraging the Lorentz manifold's exponential expansion for trajectory decoupling.<n>Our codes and models will be released.
  arXiv  Detail & Related papers  (2026-02-24T02:12:58Z)
• DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving [65.7087560656003]
  Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse.<n>We propose DiffusionDriveV2, which leverages reinforcement learning to constrain low-quality modes and explore for superior trajectories.<n>This significantly enhances the overall output quality while preserving the inherent multimodality of its core Gaussian Mixture Model.
  arXiv  Detail & Related papers  (2025-12-08T17:29:52Z)
• Mixed-Density Diffuser: Efficient Planning with Non-uniform Temporal Resolution [1.1172382217477128]
  Training models to skip steps in their trajectories helps capture long-term dependencies without additional or memory computational cost.<n>We hypothesize this temporal density threshold is non-uniform across a temporal horizon and that certain parts of a planned trajectory should be more densely planned.
  arXiv  Detail & Related papers  (2025-10-27T05:45:59Z)
• Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning [5.274804664403783]
  Strict Subgoal Execution (SSE) is a graph-based hierarchical RL framework that enforces single-step subgoal reachability.<n>We show that SSE consistently outperforms existing goal-conditioned RL and hierarchical RL approaches in both efficiency and success rate.
  arXiv  Detail & Related papers  (2025-06-26T06:35:42Z)
• Nesterov Method for Asynchronous Pipeline Parallel Optimization [59.79227116582264]
  We introduce a variant of Nesterov Accelerated Gradient (NAG) for asynchronous optimization in Pipeline Parallelism.<n>Specifically, we modify the look-ahead step in NAG to effectively address the staleness in gradients.<n>We theoretically prove that our approach converges at a sublinear rate in the presence of fixed delay in gradients.
  arXiv  Detail & Related papers  (2025-05-02T08:23:29Z)
• StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation [55.75008325187133]
  Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs)<n>StreamRL is designed with disaggregation from first principles to address two types of performance bottlenecks.<n> Experiments show that StreamRL improves throughput by up to 2.66x compared to existing state-of-the-art systems.
  arXiv  Detail & Related papers  (2025-04-22T14:19:06Z)
• Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion [62.91968752955649]
  This paper tackles a novel problem, extendable long-horizon planning-enabling agents to plan trajectories longer than those in training data without compounding errors.<n>We propose an augmentation method that iteratively generates longer trajectories by stitching shorter ones.<n>HM-Diffuser trains on these extended trajectories using a hierarchical structure, efficiently handling tasks across multiple temporal scales.
  arXiv  Detail & Related papers  (2025-03-25T22:52:46Z)
• Generative Trajectory Stitching through Diffusion Composition [29.997765496994457]
  CompDiffuser is a novel generative approach that can solve new tasks by learning to compositionally stitch together shorter trajectory chunks from previously seen tasks.<n>We conduct experiments on benchmark tasks of various difficulties, covering different environment sizes, agent state dimension, trajectory types, training data quality, and show that CompDiffuser significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2025-03-07T05:22:52Z)
• Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion [55.185588994883226]
  We introduce VQ-LCMD, a continuous-space latent diffusion framework within the embedding space that stabilizes training.<n>VQ-LCMD uses a novel training objective combining the joint embedding-diffusion variational lower bound with a consistency-matching (CM) loss.<n>Experiments show that the proposed VQ-LCMD yields superior results on FFHQ, LSUN Churches, and LSUN Bedrooms compared to discrete-state latent diffusion models.
  arXiv  Detail & Related papers  (2024-10-18T09:12:33Z)
• Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks [12.239868705130178]
  We propose a data-driven hierarchical framework that generates and updates plans based on instruction specified by linear temporal logic (LTL) Our method decomposes temporal tasks into chain of options with hierarchical reinforcement learning from offline non-expert datasets. We devise a determinantal-guided posterior sampling technique during batch generation, which improves the speed and diversity of diffusion generated options.
  arXiv  Detail & Related papers  (2024-10-03T11:10:37Z)
• PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer [47.924941959320996]
  We propose a hierarchical planner designed for offline RL called PlanDQ. PlanDQ incorporates a diffusion-based planner at the high level, named D-Conductor, which guides the low-level policy through sub-goals. At the low level, we used a Q-learning based approach called the Q-Performer to accomplish these sub-goals.
  arXiv  Detail & Related papers  (2024-06-10T20:59:53Z)
• ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge [63.00793292863]
  ToddlerDiffusion is a novel approach to decomposing the complex task of RGB image generation into simpler, interpretable stages. Our method, termed ToddlerDiffusion, cascades modality-specific models, each responsible for generating an intermediate representation. ToddlerDiffusion consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-11-24T15:20:01Z)
• Deoscillated Graph Collaborative Filtering [74.55967586618287]
  Collaborative Filtering (CF) signals are crucial for a Recommender System(RS) model to learn user and item embeddings. Recent Graph Neural Networks(GNNs) propose to stack multiple aggregation layers to propagate high-order signals. We propose a new RS model, named as textbfDeoscillated textbfGraph textbfCollaborative textbfFiltering(DGCF)
  arXiv  Detail & Related papers  (2020-11-04T02:26:53Z)

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.