Geometry-Aligned LLM Fine-Tuning for Sequential Narrow-Opening Planning

• URL: http://arxiv.org/abs/2603.16028v1
• Date: Tue, 17 Mar 2026 00:24:32 GMT
• Title: Geometry-Aligned LLM Fine-Tuning for Sequential Narrow-Opening Planning
• Abstract summary: We study rigid-body motion planning through multiple sequential narrow openings.<n>To achieve this, we propose a geometry-aligned large language model (LLM) fine-tuning framework.<n>Our method achieves the highest success rate in both in-distribution and out-of-distribution environments.
• Score: 6.579320299248572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study rigid-body motion planning through multiple sequential narrow openings, which requires long-horizon geometric reasoning because the configuration used to traverse an early opening constrains the set of reachable configurations for subsequent ones. To achieve this, we propose a geometry-aligned large language model (LLM) fine-tuning framework that generates fixed-length, machine-readable waypoint sequences that are both geometrically feasible and coordinated across openings. Our approach uses a bi-level training pipeline. First, we perform failure-driven LoRA supervised fine-tuning (SFT) on human demonstrations, which incorporates structured failure feedback to teach the model common failure modes and enforce the output format. Second, we refine the same LoRA adapters using Group Relative Policy Optimization (GRPO) with geometric verification: each sampled waypoint sequence is densified by a model-based planner and scored with a deterministic geometry-derived reward to achieve continuous-motion feasibility. To validate the effectiveness of our proposed method, we provide both quantitative and qualitative results from simulations. Our method achieves the highest success rate in both in-distribution and out-of-distribution environments and qualitatively exhibits long-horizon geometric reasoning by selecting exit poses that facilitate entry into subsequent openings.

Related papers

• Model Merging by Output-Space Projection [6.752805486904705]
  Model merging combines fine-tuned checkpoints into a single multi-task model without retraining.<n>We show that merging can be formulated as a convex programme over residual updates.<n>We extend to multi-layer merging via a sequential layer-wise algorithm and demonstrate consistent gains across language and vision benchmarks.
  arXiv  Detail & Related papers  (2026-05-27T21:01:29Z)
• Fitting Unknown Number of Hyperplanes with Manifold Optimization [57.48093263119306]
  Fitting unknown number of linearplanes to data is a fundamental yet challenging problem in machine learning.<n>Existing approaches often struggle with optimum optima or lack geometric consistency.
  arXiv  Detail & Related papers  (2026-05-27T14:02:20Z)
• Barrier-enforced multi-objective optimization for direct point and sharp interval forecasting [1.0966260566122237]
  This paper proposes a multi-step probabilistic forecasting framework using a single neural-network based model to generate simultaneous point and interval forecasts.<n>Our approach ensures non-crossing prediction intervals (PIs) through a model structure design that strictly satisfy a target coverage probability (PICP)<n>Results demonstrate that our proposed loss consistently outperforms those in current literature by achieving target coverage with the narrowest PI widths.
  arXiv  Detail & Related papers  (2026-04-20T16:43:12Z)
• Differentiable Object Pose Connectivity Metrics for Regrasp Sequence Optimization [13.078429762098631]
  Regrasp planning is often required when one pick-and-place cannot transfer an object from an initial pose to a goal pose.<n>We propose an implicit multi-step regrasp planning framework based on differentiable pose sequence connectivity metrics.
  arXiv  Detail & Related papers  (2026-04-16T07:47:57Z)
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• Two-Stage Path Following for Mobile Manipulators via Dimensionality-Reduced Graph Search and Numerical Optimization [13.862491697262037]
  Efficient path following for mobile manipulators is often hindered by high-dimensional configuration spaces and kinematic constraints.<n>This paper presents a robust two-stage configuration planning framework that decouples the 8-DoF planning problem into a tractable 2-DoF base optimization.
  arXiv  Detail & Related papers  (2026-03-07T02:54:02Z)
• Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing [1.0312968200748118]
  Rectified Flow models achieve state-of-the-art generation quality, yet controlling them for precise tasks remains a challenge.<n>Current approaches bifurcate into inversion-based guidance, which suffers from "geometric locking"<n>We propose Score-Guided Proximal Projection, a unified framework that bridges the gap between deterministic optimization and contraction sampling.
  arXiv  Detail & Related papers  (2026-03-05T23:44:45Z)
• Orthogonalized Policy Optimization:Decoupling Sampling Geometry from Optimization Geometry in RLHF [0.0]
  Large language model alignment objectives are often presented as a collection of distinct algorithms, such as PPO, DPO, IPO, and their variants.<n>In this work, we argue that this diversity obscures a simpler underlying structure.<n>We show that this entanglement is not merely a modeling convenience but a source of systematic instability.
  arXiv  Detail & Related papers  (2026-01-18T13:57:44Z)
• FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM [50.9765003472032]
  FoundationSLAM is a learning-based monocular dense SLAM system for accurate and robust tracking and mapping.<n>Our core idea is to bridge flow estimation with reasoning by leveraging the guidance from foundation depth models.
  arXiv  Detail & Related papers  (2025-12-31T17:57:45Z)
• Parallel Test-Time Scaling for Latent Reasoning Models [58.428340345068214]
  Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs)<n>Recent advances in latent reasoning, where intermediate reasoning unfolds in continuous vector spaces, offer a more efficient alternative to explicit Chain-of-Thought.<n>This work enables parallel TTS for latent reasoning models by addressing the above issues.
  arXiv  Detail & Related papers  (2025-10-09T03:33:00Z)
• DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling [56.45844907505722]
  We propose DecoupleSearch, a framework that decouples planning and search processes using dual value models.<n>Our approach constructs a reasoning tree, where each node represents planning and search steps.<n>During inference, Hierarchical Beam Search iteratively refines planning and search candidates with dual value models.
  arXiv  Detail & Related papers  (2025-09-07T13:45:09Z)
• GeometryZero: Improving Geometry Solving for LLM with Group Contrastive Policy Optimization [63.107398132743825]
  Group Contrastive Policy Optimization (GCPO) is a novel reinforcement learning framework featuring two key innovations.<n>We develop GeometryZero, a family of affordable-size geometric reasoning models that judiciously determine when to employ auxiliary construction.
  arXiv  Detail & Related papers  (2025-06-08T14:18:15Z)
• Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design [17.7006862812979]
  We propose a Sequential Monte Carlo framework that enables scalable inference-time control of discrete diffusion models.<n>Specifically, our approach derives tractable importance weights for a range of intermediate targets and characterises the optimal proposal.<n> Empirical results across synthetic tasks, language modelling, biology design, and text-to-image generation demonstrate that our framework enhances controllability and sample quality.
  arXiv  Detail & Related papers  (2025-05-28T16:12:03Z)

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.