Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely

• URL: http://arxiv.org/abs/2605.31387v1
• Date: Fri, 29 May 2026 14:51:49 GMT
• Title: Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely
• Abstract summary: Vision-language models (VLMs) support robotic tasks involving visual interpretation, question answering, and instruction following.<n>We study this gap through a collaborative structure-building task that combines visual interpretation, grounding, language-guided interaction, and action generation.
• Score: 17.22551679328024
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Robots operating in diverse environments rely on visual input to interpret objects and spatial layouts. In human-collaborative tasks, they are expected to communicate this understanding through language. Vision-language models (VLMs) support robotic tasks involving visual interpretation, question answering, and instruction following, but their capabilities in collaborative dialogue tasks requiring spatial reasoning remain underexplored. We study this gap through a collaborative structure-building task that combines visual interpretation, grounding, language-guided interaction, and action generation. We develop a framework in which VLMs use dialogue to reconstruct a target structure from visual and textual inputs. We evaluate open-weight and closed VLMs across interaction settings, input modalities, and image representations. Results show that spatial reasoning over visual representations remains difficult for the evaluated VLMs. Detailed text representations of the target yield higher reconstruction success across modality conditions, while decomposed image representations improve performance. These findings reveal limits in visual spatial grounding and grounded instruction generation for collaborative VLM agents.

Related papers

• AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models [15.021275200375504]
  This study investigates the challenge of ambiguity faced by Vision-Language Models (VLMs) in understanding spatial semantics.<n>Natural language descriptions of spatial relations frequently omit explicit reference frames, leading to semantic ambiguity and potentially serious errors for embodied AI robots.<n>We construct a new dataset, AlloEgo-View, comprising (image, query, view-specific answer) triplets that capture key object relations from both allocentric and egocentric perspectives.<n>We develop AlloEgo-VLM, a framework to disambiguate allocentric and egocentric reference frames, even under ambiguous queries, and to be easily integrated
  arXiv  Detail & Related papers  (2026-08-16T08:06:20Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching [25.883546163390957]
  We endow CLIP with fine-grained action-level understanding by incorporating action-related external knowledge generated by large language models (LLMs)<n>We propose an adaptive interaction module to aggregate attentive visual features conditioned on action-aware prompted knowledge for establishing discriminative and action-aware visual representations.
  arXiv  Detail & Related papers  (2025-06-30T03:49:08Z)
• Spatial Understanding from Videos: Structured Prompts Meet Simulation Data [89.77871049500546]
  We present a unified framework for enhancing 3D spatial reasoning in pre-trained vision-language models without modifying their architecture.<n>This framework combines SpatialMind, a structured prompting strategy that decomposes complex scenes and questions into interpretable reasoning steps, with ScanForgeQA, a scalable question-answering dataset built from diverse 3D simulation scenes.
  arXiv  Detail & Related papers  (2025-06-04T07:36:33Z)
• Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning [27.511627003202538]
  Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes.<n>This paper addresses two key challenges: (1) conventional detection-to-construction methods produce unfocused, contextually irrelevant relationship sets, and (2) existing approaches fail to form persistent memories for generalizing interaction reasoning to new scenes.<n>We propose Interaction-augmented Scene Graph Reasoning (ISGR), a framework that enhances VLMs' interactional reasoning through three complementary components.
  arXiv  Detail & Related papers  (2025-05-14T04:04:23Z)
• V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models [84.27290155010533]
  We introduce Vision-centric Multiple Abilities Game Evaluation (V-MAGE), a novel game-based evaluation framework.<n>V-MAGE features five distinct video games comprising over 30 carefully constructed evaluation scenarios.<n>We show V-MAGE provides actionable insights for improving the visual and reasoning capabilities of MLLMs in dynamic, interactive settings.
  arXiv  Detail & Related papers  (2025-04-08T15:43:01Z)
• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding [79.43306110124875]
  AlignVLM is a vision-text alignment method that maps visual features to a weighted average of text embeddings.<n>Our experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods.
  arXiv  Detail & Related papers  (2025-02-03T13:34:51Z)
• Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering [10.505845766495128]
  Multimodal large language models (MLLMs) have made significant progress in integrating visual and textual modalities.<n>We propose a novel framework based on multimodal retrieval-augmented generation (RAG)<n>RAG introduces structured scene graphs to enhance object recognition, relationship identification, and spatial understanding within images.
  arXiv  Detail & Related papers  (2024-12-30T13:16:08Z)
• VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use [74.39058448757645]
  We present VipAct, an agent framework that enhances vision-language models (VLMs) VipAct consists of an orchestrator agent, which manages task requirement analysis, planning, and coordination, along with specialized agents that handle specific tasks. We evaluate VipAct on benchmarks featuring a diverse set of visual perception tasks, with experimental results demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2024-10-21T18:10:26Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting [97.52388851329667]
  We introduce Marking Open-world Keypoint Affordances (MOKA) to solve robotic manipulation tasks specified by free-form language instructions. Central to our approach is a compact point-based representation of affordance, which bridges the VLM's predictions on observed images and the robot's actions in the physical world. We evaluate and analyze MOKA's performance on various table-top manipulation tasks including tool use, deformable body manipulation, and object rearrangement.
  arXiv  Detail & Related papers  (2024-03-05T18:08:45Z)
• Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects [11.117055725415446]
  Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. The absence of fine-grained visual object detection hinders the model from understanding the details of images, leading to irreparable visual hallucinations and factual errors. We propose Lyrics, a novel multi-modal pre-training and instruction fine-tuning paradigm that bootstraps vision-language alignment from fine-grained cross-modal collaboration.
  arXiv  Detail & Related papers  (2023-12-08T09:02:45Z)
• Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution [0.0]
  We consider the task of visual grounding, where the agent segments an object from a crowded scene given a natural language description. Modern holistic approaches to visual grounding usually ignore language structure and struggle to cover generic domains. We introduce a fully decoupled modular framework for compositional visual grounding of entities, attributes, and spatial relations.
  arXiv  Detail & Related papers  (2022-05-24T14:12:32Z)

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.