Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kranti, Chalamalasetti, Hakimov, Sherzod, Schlangen, David
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming
por: Kranti, Chalamalasetti, et al.
Publicado: (2024)

From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning
por: Kranti, Chalamalasetti, et al.
Publicado: (2025)

clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations
por: Kranti, Chalamalasetti, et al.
Publicado: (2025)

Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft
por: Kranti, Chalamalasetti, et al.
Publicado: (2024)

A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench
por: Schlangen, David, et al.
Publicado: (2025)

clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents
por: Beyer, Anne, et al.
Publicado: (2024)

Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies
por: Sadler, Philipp, et al.
Publicado: (2024)

Learning Communication Policies for Different Follower Behaviors in a Collaborative Reference Game
por: Sadler, Philipp, et al.
Publicado: (2024)

The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue
por: Hakimov, Sherzod, et al.
Publicado: (2026)

Ad-hoc Concept Forming in the Game Codenames as a Means for Evaluating Large Language Models
por: Hakimov, Sherzod, et al.
Publicado: (2025)

Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment
por: Jordan, Jonathan, et al.
Publicado: (2025)

How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics
por: Bhavsar, Nidhir, et al.
Publicado: (2024)

MetricalARGS: A Taxonomy for Studying Metrical Poetry with LLMs
por: Kranti, Chalamalasetti, et al.
Publicado: (2025)

MATA: Mindful Assessment of the Telugu Abilities of Large Language Models
por: Kranti, Chalamalasetti, et al.
Publicado: (2025)

TurkicNLP: An NLP Toolkit for Turkic Languages
por: Hakimov, Sherzod
Publicado: (2026)

The Price of Thought: A Multilingual Analysis of Reasoning, Performance, and Cost of Negotiation in Large Language Models
por: Hakimov, Sherzod, et al.
Publicado: (2025)

Mind the Gap: Evaluating LLM Understanding of Human-Taught Road Safety Principles
por: Kranti, Chalamalasetti
Publicado: (2025)

A Dialogue Game for Eliciting Balanced Collaboration
por: Jeknić, Isidora, et al.
Publicado: (2024)

Unveiling Global Narratives: A Multilingual Twitter Dataset of News Media on the Russo-Ukrainian Conflict
por: Hakimov, Sherzod, et al.
Publicado: (2023)

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
por: Chen, Boyuan, et al.
Publicado: (2024)

Using Game Play to Investigate Multimodal and Conversational Grounding in Large Multimodal Models
por: Hakimov, Sherzod, et al.
Publicado: (2024)

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
por: Wang, Kangrui, et al.
Publicado: (2025)

M2SA: Multimodal and Multilingual Model for Sentiment Analysis of Tweets
por: Thakkar, Gaurish, et al.
Publicado: (2024)

Test Set Quality in Multilingual LLM Evaluation
por: Kranti, Chalamalasetti, et al.
Publicado: (2025)

Can Visual Dialogue Models Do Scorekeeping? Exploring How Dialogue Representations Incrementally Encode Shared Knowledge
por: Madureira, Brielen, et al.
Publicado: (2022)

A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment
por: Inoue, Koji, et al.
Publicado: (2025)

Coherence-Driven Multimodal Safety Dialogue with Active Learning for Embodied Agents
por: Hassan, Sabit, et al.
Publicado: (2024)

Free-text Rationale Generation under Readability Level Control
por: Hsu, Yi-Sheng, et al.
Publicado: (2024)

SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues
por: Kuo, Martin, et al.
Publicado: (2025)

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
por: Dai, Yuqin, et al.
Publicado: (2026)

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
por: Zhang, Yang, et al.
Publicado: (2024)

Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
por: Badola, Kartikeya, et al.
Publicado: (2025)

REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation
por: Yuan, Puzhen, et al.
Publicado: (2025)

PoseLess: Depth-Free Vision-to-Joint Control via Direct Image Mapping with VLM
por: Dao, Alan, et al.
Publicado: (2025)

When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality
por: Madureira, Brielen, et al.
Publicado: (2024)

Leveraging Adaptive Group Negotiation for Heterogeneous Multi-Robot Collaboration with Large Language Models
por: Song, Siqi, et al.
Publicado: (2025)

Autonomous Frontier-Based Exploration with VLM Guidance
por: Aitha, Aarush, et al.
Publicado: (2026)

Dialogue with Robots: Proposals for Broadening Participation and Research in the SLIVAR Community
por: Kennington, Casey, et al.
Publicado: (2024)

Applying General Turn-taking Models to Conversational Human-Robot Interaction
por: Skantze, Gabriel, et al.
Publicado: (2025)

Multi-Agent Consensus Seeking via Large Language Models
por: Chen, Huaben, et al.
Publicado: (2023)