AntEval: Quantitatively Evaluating Informativeness and Expressiveness of Agent Social Interactions

While Large Language Models (LLMs) based agents have successfully mimicked human behaviors in various scenarios, the realm of complex, multi-character social interactions within extended contexts remains underexplored. The challenge is compounded by privacy concerns, making it difficult to capture and utilize intricate real-life interactions. More importantly, the absence of quantitative evaluation methods hampers the pursuit of high-quality agent interactions, often leading to interactions that are limited in informativeness and expressiveness, characterized by superficial small talk without clear intentions. In this work, we leverage the rules of Tabletop Role-Playing Games (TRPG) to create an environment conducive to complex, context-rich interactions, emphasizing informativeness and expressiveness. This virtual setting alleviates privacy concerns and motivates agents to engage in meaningful, high-quality interactions as part of their in-game objectives. To assess these interactions, we introduce the Agent interaction Evaluation framework (AntEval), targeting the qualitative evaluation of interaction informativeness and expressiveness. Specifically, we propose two novel evaluation metrics: Information Exchanging Precision (IEP) and Interaction Expressiveness Gap (IEG). These metrics are designed to assess interactions in scenarios focused on information exchange and intention expression, respectively. Our experimental results demonstrate the effectiveness of these metrics in evaluating interaction quality. Notably, we identify significant areas for improvement in LLMs regarding social interactions, as highlighted by our metrics. We believe AntEval will guide further exploration in complex agent interactions, bringing them closer to emulating real human behavior and enhancing their integration and utility in real-world applications.

Tachikuma: Understading Complex Interactions with Multi-Character and Novel Objects by Large Language Models

Recent advancements in natural language and Large Language Models (LLMs) have enabled AI agents to simulate human-like interactions within virtual worlds. However, these interactions still face limitations in complexity and flexibility, particularly in scenarios involving multiple characters and novel objects. Pre-defining all interactable objects in the agent's world model presents challenges, and conveying implicit intentions to multiple characters through complex interactions remains difficult. To address these issues, we propose integrating virtual Game Masters (GMs) into the agent's world model, drawing inspiration from Tabletop Role-Playing Games (TRPGs). GMs play a crucial role in overseeing information, estimating players' intentions, providing environment descriptions, and offering feedback, compensating for current world model deficiencies. To facilitate future explorations for complex interactions, we introduce a benchmark named Tachikuma, comprising a Multiple character and novel Object based interaction Estimation (MOE) task and a supporting dataset. MOE challenges models to understand characters' intentions and accurately determine their actions within intricate contexts involving multi-character and novel object interactions. Besides, the dataset captures log data from real-time communications during gameplay, providing diverse, grounded, and complex interactions for further explorations. Finally, we present a simple prompting baseline and evaluate its performance, demonstrating its effectiveness in enhancing interaction understanding. We hope that our dataset and task will inspire further research in complex interactions with natural language, fostering the development of more advanced AI agents.

Rethinking Visual Relationships for High-level Image Understanding

Relationships, as the bond of isolated entities in images, reflect the interaction between objects and lead to a semantic understanding of scenes. Suffering from visually-irrelevant relationships in current scene graph datasets, the utilization of relationships for semantic tasks is difficult. The datasets widely used in scene graph generation tasks are splitted from Visual Genome by label frequency, which even can be well solved by statistical counting. To encourage further development in relationships, we propose a novel method to mine more valuable relationships by automatically filtering out visually-irrelevant relationships. Then, we construct a new scene graph dataset named Visually-Relevant Relationships Dataset (VrR-VG) from Visual Genome. We evaluate several existing methods in scene graph generation in our dataset. The results show the performances degrade significantly compared to the previous dataset and the frequency analysis do not work on our dataset anymore. Moreover, we propose a method to learn feature representations of instances, attributes, and visual relationships jointly from images, then we apply the learned features to image captioning and visual question answering respectively. The improvements on the both tasks demonstrate the efficiency of the features with relation information and the richer semantic information provided in our dataset.