InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

LLMs have shown strong performance on human-centric reasoning tasks. While previous evaluations have explored whether LLMs can infer intentions or detect deception, they often overlook the individualized reasoning styles that influence how people interpret and act in social contexts. Social deduction games (SDGs) provide a natural testbed for evaluating individualized reasoning styles, where different players may adopt diverse but contextually valid reasoning strategies under identical conditions. To address this, we introduce InMind, a cognitively grounded evaluation framework designed to assess whether LLMs can capture and apply personalized reasoning styles in SDGs. InMind enhances structured gameplay data with round-level strategy traces and post-game reflections, collected under both Observer and Participant modes. It supports four cognitively motivated tasks that jointly evaluate both static alignment and dynamic adaptation. As a case study, we apply InMind to the game Avalon, evaluating 11 state-of-the-art LLMs. 1 Generalpurpose LLMs, even GPT-4o frequently rely on lexical cues, struggling to anchor reflections in temporal gameplay or adapt to evolving strategies. In contrast, reasoning-enhanced LLMs like DeepSeek-R1 exhibit early signs of stylesensitive reasoning. These findings reveal key limitations in current LLMs' capacity for individualized, adaptive reasoning, and position InMind as a step toward cognitively aligned human-AI interaction. Emerging research (Strachan et al., 2024; Mittelstädt et al., 2024) further highlights their promising performance in human-centric tasks, including social commonsense inference, intention recognition, and belief attribution. Beyond these capabilities, recent studies suggest that LLMs may exhibit early signs of Theory of Mind (ToM)-the ability to represent and reason about others ' beliefs, desires, and intentions (Sarıtaş et al., 2025; Kim et al., 2025) . Understanding and evaluating such high-level cognitive traits is critical for advancing LLMs toward artificial general intelligence (AGI), and potentially, artificial superintelligence. Existing benchmarks attempt to assess ToMlike reasoning through tasks such as intent classification (Liu et al., 2024) , false-belief attribu-