arXiv AI June 17, 2026 By Peter Zeng, Weiling Li, Amie Paige, Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras, Gregory Zelinsky, Susan Brennan, Owen Rambow

LVLMs and Humans Ground Differently in Referential Communication

Read the original on arXiv AI →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

agents

arXiv AI

Jun 17

Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

arXiv:2606. 17372v1 Announce Type: cross Abstract: Two recent studies (Jones et al.

By Peter Zeng, Amie J. Paige, Weiling Li, Susan E. Brennan, Owen Rambow, Cameron R. Jones

llms

arXiv AI

Jun 9

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.

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

llms agents multimodal safety

arXiv AI

22h ago

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

arXiv:2608. 17605v1 Announce Type: cross Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction.

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

agents multimodal benchmarks safety

arXiv AI

Jul 29

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension

arXiv:2512. 06276v3 Announce Type: replace-cross Abstract: Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description.

By Tianyi Gao, Hao Li, Han Fang, Xin Wei, Xiaodong Dong, Hongbo Sun, Ye Yuan, Zhongjiang He, Jinglin Xu, Jingmin Xin, Hao Sun

llms reinforcement-learning multimodal benchmarks

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

Hugging Face Trending Papers

Jun 22

PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models

Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large language models (MLLMs).

llms multimodal benchmarks

Related stories

Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication

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

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

RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension

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

PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models