SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation

• URL: http://arxiv.org/abs/2511.00054v1
• Date: Tue, 28 Oct 2025 16:33:50 GMT
• Title: SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
• Abstract summary: SpatialTraceGen is a framework to distill the reasoning processes of a large teacher model into a high-quality dataset of multi-hop, multi-tool reasoning traces.<n>A key innovation is our automated Verifier, which scalably ensures the fidelity of each reasoning step.<n>On the CLEVR-Humans benchmark, this verifier-guided process improves the average quality score of traces by 17% while reducing quality variance by over 40%.
• Score: 0.8749675983608171
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Vision-Language Models (VLMs) excel in many areas, they struggle with complex spatial reasoning, which requires problem decomposition and strategic tool use. Fine-tuning smaller, more deployable models offers an efficient path to strong performance, but this is hampered by a major bottleneck: the absence of high-quality, step-by-step reasoning data. To address this data-efficiency gap, we introduce SpatialTraceGen, a framework to distill the reasoning processes of a large teacher model into a high-quality dataset of multi-hop, multi-tool reasoning traces. A key innovation is our automated Verifier, which scalably ensures the fidelity of each reasoning step, providing a cost-effective alternative to manual human annotation. On the CLEVR-Humans benchmark, this verifier-guided process improves the average quality score of traces by 17\% while reducing quality variance by over 40\%. SpatialTraceGen delivers a dataset of expert traces, providing the structured, step-by-step examples of tool use necessary for effective fine-tuning and sample-efficient offline reinforcement learning.

Related papers

• Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning [16.95900718416944]
  We introduce a novel Bidirectional Curriculum Generation framework to maximize the instructional value of every training sample.<n>Unlike rigid trajectories, our multi-agent ecosystem mimics adaptive pedagogy to establish a closed feedback loop.<n>This mechanism ensures that the model consumes only the most effective data at any given stage.
  arXiv  Detail & Related papers  (2026-03-05T12:49:21Z)
• Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning [65.10602992874787]
  AutoTraj is a framework that automatically learns TIR by repairing and rewarding tool-use trajectories.<n> Experiments on real-world benchmarks demonstrate the effectiveness of AutoTraj.
  arXiv  Detail & Related papers  (2026-01-30T14:42:04Z)
• LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning [12.792070502265616]
  Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields.<n>Such data often contains numerous low-quality samples, necessitating effective data processing (DP)
  arXiv  Detail & Related papers  (2026-01-28T08:37:34Z)
• InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities [27.09178257629886]
  InfiAlign is a scalable and sample-efficient post-training framework for large language models (LLMs)<n>At the core of InfiAlign is a robust data selection pipeline that automatically curates high-quality alignment data from open-source reasoning.<n>Our results highlight the effectiveness of combining principled data selection with full-stage post-training.
  arXiv  Detail & Related papers  (2025-08-07T15:34:06Z)
• Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration [6.7181844004432385]
  We introduce a novel parameter-efficient learning methodology that incorporates uncertainty calibration loss within the Active Learning framework.<n>We demonstrate that our solution can match and exceed the performance of complex feature-based sampling techniques.
  arXiv  Detail & Related papers  (2025-07-29T06:08:28Z)
• SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning [29.14330314090061]
  Imitation learning advances robot capabilities by enabling the acquisition of diverse behaviors from human demonstrations.<n>Existing robotic curation approaches rely on costly manual annotations and perform curation at a coarse granularity.<n>We introduce SCIZOR, a self-supervised data curation framework that filters out low-quality state-action pairs to improve the performance of imitation learning policies.
  arXiv  Detail & Related papers  (2025-05-28T17:45:05Z)
• Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark [62.58869921806019]
  We propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset. We design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline.
  arXiv  Detail & Related papers  (2024-11-23T08:06:06Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)
• Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate [105.86576388991713]
  We introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives.<n>We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets.
  arXiv  Detail & Related papers  (2024-10-29T14:41:44Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Few-shot Quality-Diversity Optimization [50.337225556491774]
  Quality-Diversity (QD) optimization has been shown to be effective tools in dealing with deceptive minima and sparse rewards in Reinforcement Learning. We show that, given examples from a task distribution, information about the paths taken by optimization in parameter space can be leveraged to build a prior population, which when used to initialize QD methods in unseen environments, allows for few-shot adaptation. Experiments carried in both sparse and dense reward settings using robotic manipulation and navigation benchmarks show that it considerably reduces the number of generations that are required for QD optimization in these environments.
  arXiv  Detail & Related papers  (2021-09-14T17:12:20Z)

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.