2.5-D Decomposition for LLM-Based Spatial Construction

• URL: http://arxiv.org/abs/2605.07066v1
• Date: Fri, 08 May 2026 00:17:33 GMT
• Title: 2.5-D Decomposition for LLM-Based Spatial Construction
• Abstract summary: Large language models (LLMs) make systematic coordinate errors when generating three-dimensional block placements.<n>We present a neuro-symbolic pipeline based on emph2.5-D decomposition.<n>A deterministic executor computes all vertical placement from column occupancy, eliminating an entire class of errors.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous systems that build structures from natural-language instructions need reliable spatial reasoning, yet large language models (LLMs) make systematic coordinate errors when generating three-dimensional block placements. We present a neuro-symbolic pipeline based on \emph{2.5-D decomposition}: the LLM plans in the two-dimensional horizontal plane while a deterministic executor computes all vertical placement from column occupancy, eliminating an entire class of errors. On the Build What I Mean benchmark (160 rounds), GPT-4o-mini with this pipeline achieves 94.6\% mean structural accuracy across 12 independent runs, within 3.0 percentage points of the 97.6\% ceiling imposed by architect-agent errors that no builder-side improvement can address. This outperforms both GPT-4o at 90.3\% and the best competing system at 76.3\%. A controlled ablation confirms that 2.5-D decomposition is the dominant contributor, accounting for 50.7 percentage points of accuracy. The pipeline transfers directly to edge hardware: Nemotron-3 120B running locally on an NVIDIA Jetson Thor AGX matches the cloud result at 94.5\% with no prompt modifications. The underlying principle, removing deterministic dimensions from the LLM's output space, applies to any autonomous construction or assembly task where gravity or other physical constraints fix one or more degrees of freedom. A transfer experiment on 500 IGLU collaborative building tasks confirm the effect generalizes beyond the primary benchmark.

Related papers

• From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix [55.08143827481755]
  We consolidate traffic from over 200 internal applications onto a single model.<n>We train a separate GRPO expert per axis and merge them via two-stage SLERP.<n>The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.
  arXiv  Detail & Related papers  (2026-09-01T17:39:26Z)
• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study [48.83701310501069]
  This paper investigates whether a single recipe is sufficient for heterogeneous architecture pools, or whether the optimal pairing varies across structurally diverse models.<n>We conduct a systematic empirical study of all $3 times 6 = 18$ combinations of six classifiers paired with three loss functions: Cross-Entropy (CEL), Negative Log-Likelihood (NLL), and the recently introduced genetically evolved NGL loss across the base models presented in LEMUR heterogeneous architecture pool on six image classification datasets.<n>Our results confirm that no single pairing is universally optimal. Cross-Entropy with Adam or AdamW is the most robust choice across
  arXiv  Detail & Related papers  (2026-06-18T20:51:42Z)
• RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM Agents [0.0]
  RAIL Guard is a closed-loop responsible AI pipeline.<n>It iteratively remediates failing outputs through an evaluate-rewrite-reevaluate loop.<n>System is available as open-source SDKs.
  arXiv  Detail & Related papers  (2026-05-28T21:23:49Z)
• A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection [0.42970700836450487]
  This paper describes a decoupled, edge-deployable pipeline for wind turbine blade inspection.<n>The Eyes a Y26-x-obb oriented bounding-box localizes defects at dataset-native resolution.<n>The Bridge a deterministic, parameter-free encoding module maps each detected bounding box to grid-referenced tokens.
  arXiv  Detail & Related papers  (2026-05-26T04:27:38Z)
• ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning [5.523132953818281]
  We present ReFlect, a system for LLM reasoning that creates standalone error detection and recovery logic as a deterministic wrapper around the model.<n> Controlled experiments across 6 reasoning domains show that prompt-level self-critique produces formulaic templates that flag no issues in 90 of 100 audited reflection blocks.<n>Our ReFlect harness achieves task success rates ranging from 41% on GPT-4o-mini to 56% on Claude Sonnet 4.5 across six models spanning small and frontier scale.
  arXiv  Detail & Related papers  (2026-05-07T06:29:34Z)
• Paired-CSLiDAR: Height-Stratified Registration for Cross-Source Aerial-Ground LiDAR Pose Refinement [46.13526676100776]
  We introduce Paired-CSLiDAR, a cross-source aerial-ground LiDAR benchmark for single-scan pose refinement.<n>The benchmark contains 12,683 ground-aerial pairs across 6 evaluation sites.<n>We propose Residual-Guided Stratified Registration (RGSR), a training-free, geometry-only refinement pipeline.
  arXiv  Detail & Related papers  (2026-05-01T13:14:20Z)
• Authority Inversion in LLM-Mediated Ubiquitous Systems: When Models Trust Users Over Sensors [6.414826816896125]
  We investigate how large language models implicitly allocate authority when sensor measurements and user claims conflict remain unexamined.<n>We find numerical sensor data fails to integrate into answer-relevant model directions, allowing natural-language claims to dominate the final decision.<n>We propose Geometric Authority (GAC) as an inference-time layer-level intervention to suppress misplaced user authority.
  arXiv  Detail & Related papers  (2026-04-28T04:59:03Z)
• THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture [0.0]
  THEIA is a 2.75M modular neural architecture that learns the complete Kleene three-valued logic (K3) truth table from task data without external symbolic inference or hand-encoded K3 gate primitives.<n> Transformer baselines also reach >99% on all 39 rules, and flats match THEIA on Phase-1 accuracy within 0.04pp.
  arXiv  Detail & Related papers  (2026-04-13T10:44:15Z)
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels [49.35636088613484]
  Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces.<n>We introduce LeModelWorld, the first JEPA that trains stably end-to-end from raw pixels using only two loss terms.<n>With 15M parameters trainable on a single GPU in a few hours, LeWM plans up to 48x faster than foundation-model-based world models.
  arXiv  Detail & Related papers  (2026-03-13T19:48:14Z)
• Interpretable-by-Design Transformers via Architectural Stream Independence [1.2891210250935148]
  We investigate whether architectural constraints can enforce interpretability by design through architectural stream independence.<n>We validate this principle through the Late Fusion Architecture (LFA), which demonstrates interpretable symbolic heads through all the final layers.<n>We quantify this effect by introducing the Token-Position Dependence Score (PDS), with $PDS_max$ = 0.276 and 0.058 respectively.
  arXiv  Detail & Related papers  (2026-03-08T05:44:18Z)
• JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation [46.64215658042213]
  We introduce Joint-Token (JTok) and Mixture of Joint-Token (JTok-M), which augment Transformer layers with modulation vectors retrieved from auxiliary embedding tables.<n>These vectors modulate the backbone via lightweight, element-wise operations, incurring negligible FLOPs overhead.<n>Our approach consistently reduces validation loss and significantly improves downstream task performance.
  arXiv  Detail & Related papers  (2026-01-31T16:15:18Z)
• Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation [46.34608916687127]
  Low-Rank Decomposed Scaling (LoRDS) is a unified framework that rethinks quantization granularity through this low-rank decomposition.<n>By "breaking the blocks" of spatial constraints, LoRDS establishes a seamless efficiency lifecycle.<n>LoRDS consistently outperforms state-of-the-art baselines across various model families in both quantization and downstream fine-tuning tasks.
  arXiv  Detail & Related papers  (2026-01-30T08:46:02Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• BuildingBRep-11K: Precise Multi-Storey B-Rep Building Solids with Rich Layout Metadata [5.436963837926521]
  BuildingBRep-11K is a collection of 11 978 multi-storey (2-10 floors) buildings (about 10 GB)<n>Every sample consists of a geometrically exact B-rep solid-covering floors, walls, slabs and rule-based openings.<n>To verify the dataset's learnability we trained two lightweight PointNet baselines.
  arXiv  Detail & Related papers  (2025-06-03T03:44:34Z)

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.