Attributional inference, the ability to predict latent intentions behind observed actions, is a critical yet underexplored capability for large language models (LLMs) operating in multi-agent environments. Traditional natural language inference (NLI), in fact, fails to capture the nuanced, intention-driven reasoning essential for complex interactive systems. To address this gap, we introduce Attributional NLI (Att-NLI), a framework that extends NLI with principles from social psychology to assess an agent's capacity for abductive intentional inference (generating hypotheses about latent intentions), and subsequent deductive verification (drawing valid logical conclusions). We instantiate Att-NLI via a textual game, Undercover-V, experimenting with three types of LLM agents with varying reasoning capabilities and access to external tools: a standard NLI agent using only deductive inference, an Att-NLI agent employing abductive-deductive inference, and a neuro-symbolic Att-NLI agent performing abductive-deductive inference with external theorem provers. Extensive experiments demonstrate a clear hierarchy of attributional inference capabilities, with neuro-symbolic agents consistently outperforming others, achieving an average win rate of 17.08%. Our results underscore the role that Att-NLI can play in developing agents with sophisticated reasoning capabilities, highlighting, at the same time, the potential impact of neuro-symbolic AI in building rational LLM agents acting in multi-agent environments.

翻译：归因性推理，即预测观察到的行为背后潜在意图的能力，对于在多智能体环境中运行的大型语言模型（LLMs）而言，是一项关键但尚未得到充分探索的能力。事实上，传统的自然语言推理（NLI）无法捕捉复杂交互系统所必需的、由意图驱动的细微推理。为弥补这一不足，我们引入了归因性自然语言推理（Att-NLI），该框架将社会心理学原理融入NLI，以评估智能体进行溯因意图推理（生成关于潜在意图的假设）及后续演绎验证（得出有效逻辑结论）的能力。我们通过一个文本游戏Undercover-V来实例化Att-NLI，并实验了三种具有不同推理能力和外部工具访问权限的LLM智能体：仅使用演绎推理的标准NLI智能体、采用溯因-演绎推理的Att-NLI智能体，以及使用外部定理证明器执行溯因-演绎推理的神经符号Att-NLI智能体。大量实验表明，归因性推理能力存在清晰的层次结构，神经符号智能体始终优于其他智能体，平均胜率达到17.08%。我们的结果强调了Att-NLI在开发具有复杂推理能力的智能体方面所能发挥的作用，同时也凸显了神经符号AI在构建于多智能体环境中行动的理性LLM智能体方面的潜在影响。