paper-with-me

홈 › Papers

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

2025-10-28 · Gio Huh, Dhruv Sheth, Rayhan Zirvi, Frank Xiao arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.00054

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningSpatial Reasoning

Similar Papers 제목 키워드 기반

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

2025-01-13 · Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia 외

Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it struggles in complex spatial reasoning ta…

Spatial Reasoning

PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs

2025-09-24 · Venkat Margapuri, Garik Kazanjian, Naren Kosaraju arxiv

Large Language Models (LLMs) often struggle with maintaining coherent multi-step reasoning traces, particularly in tasks that require a structured logical flow. This work introduces a quantum-inspired approach to address…

Reinforcement Learning

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics

2025-12-15 · Enshen Zhou, Yibo Li, Jingkun An, Jiayuan Zhang 외 arxiv

Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric mea…

Thinking with Visual Grounding

2026-06-15 · Junkai Zhang, Yihe Deng, Kai-Wei Chang, Wei Wang arxiv

Visual thinking should not only sound right; it should show its evidence. While recent vision-language models (VLMs) can produce natural-language reasoning traces, these traces often leave the supporting image regions im…

Reinforcement LearningSpatial ReasoningVisual ReasoningVisual Grounding

ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning

2026-01-08 · Minda Hu, Zexuan Qiu, Zenan Xu, Kun Li 외 arxiv

Recent breakthroughs in Large Reasoning Models (LRMs) have demonstrated that extensive Chain-of-Thought (CoT) generation is critical for enabling intricate cognitive behaviors, such as self-verification and backtracking,…

Reinforcement Learning