arXiv AI June 9, 2026 By Po-Ya Angela Wang, Chinmaya Mishra, Asl{\i} \"Ozy\"urek, Paula Rubio-Fern\'andez, Esam Ghaleb

Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions

arXiv:2606. 08081v1 Announce Type: cross Abstract: Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific conventions grounded in shared interaction history.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

2d ago

Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts

arXiv:2606.08081v2 Announce Type: replace-cross Abstract: Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific expressions grou...

By Po-Ya Angela Wang, Chinmaya Mishra, Asl{\i} \"Ozy\"urek, Paula Rubio-Fern\'andez, Esam Ghaleb

llms agents multimodal safety

arXiv AI

Aug 19

Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

The article surveys multi‑turn conversational AI, highlighting its shift from isolated text prompts to sustained, multimodal interactions that involve clarifying goals, revising requests, and switching topics. It reviews literature across text‑only dialogue, AudioLLMs, multimodal and omni‑modal systems, and tool‑augmented agents, organizing findings around datasets, models, training, evaluation, and cross‑cutting challenges. The analysis reveals that while multimodal perception and action have progressed rapidly, systems still struggle with persistent memory, cross‑turn grounding, full‑duplex interaction, robust evaluation, and cultural alignment.

By Syeda Faiza Ahmed, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

agents multimodal benchmarks safety

arXiv AI

Jul 1

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

arXiv:2606. 31719v1 Announce Type: cross Abstract: In collaborative dialogue, shared perception does not guarantee shared interpretation.

By Nan Li, Albert Gatt, Massimo Poesio

llms multimodal safety

arXiv AI

Jul 13

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

arXiv:2605. 12920v3 Announce Type: replace-cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world.

By Vardhan Dongre, Dilek Hakkani-T\"ur

llms agents robotics benchmarks safety

arXiv AI

Jun 17

LVLMs and Humans Ground Differently in Referential Communication

arXiv:2601. 19792v4 Announce Type: replace-cross Abstract: For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical.

By Peter Zeng, Weiling Li, Amie Paige, Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras, Gregory Zelinsky, Susan Brennan, Owen Rambow

agents

arXiv AI

Jul 14

PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging

arXiv:2604. 22823v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities.

By Zibo Shao, Baochen Xiong, Xiaoshan Yang, Yaguang Song, Qimeng Zhang, Haifeng Chen, Changsheng Xu

llms fine-tuning multimodal benchmarks safety

One email a morning, machine-written

Related stories

Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts

Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

LVLMs and Humans Ground Differently in Referential Communication

PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging