Related papers: When Reasoning Models Hurt Behavioral Simulation: …
Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…
Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack explicit reasoning or employ lengthy Chain-of-Thought…
The behavior of Large Language Models (LLMs) as artificial social agents is largely unexplored, and we still lack extensive evidence of how these agents react to simple social stimuli. Testing the behavior of AI agents in classic Game…
Psychological evidence reveals the influence of personality traits on decision-making. For instance, agreeableness is generally associated with positive outcomes in negotiations, whereas neuroticism is often linked to less favorable…
Formal logic enables computers to reason in natural language by representing sentences in symbolic forms and applying rules to derive conclusions. However, in what our study characterizes as "rulebreaker" scenarios, this method can lead to…
While LLMs have demonstrated remarkable capabilities in text generation and reasoning, their ability to simulate human decision-making -- particularly in political contexts -- remains an open question. However, modeling voter behavior…
Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversations. While recent work has explored the use of LLMs in…
Economic experiments offer a controlled setting for researchers to observe human decision-making and test diverse theories and hypotheses; however, substantial costs and efforts are incurred to gather many individuals as experimental…
Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries…
Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…
It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive…
As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly…
Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study whether large language model (LLM) agents do this in a…
Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: significant performance degradation on novel or incomplete…
When evaluating Large Language Models (LLMs) in question answering domains, it is common to ask the model to choose among a fixed set of choices (so-called multiple-choice question-answering, or MCQA). Although downstream tasks of interest…
We present SalesSim, a framework and testbed for evaluating the ability of Multimodal Large Language Models (MLLMs) to simulate realistic, persona-driven customer behavior in multi-turn, multi-modal, tool-augmented online retail…
Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs). We examined self-consistency (intra-model majority voting) and reasoning effort for…
Large language models (LLMs) are entering clinician workflows, yet evaluations rarely measure how clinician reasoning shapes model behavior during clinical interactions. We combined 61 New England Journal of Medicine Case Records with 92…
Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a…
Strategic interaction in adversarial domains such as law, diplomacy, and negotiation is mediated by language, yet most game-theoretic models abstract away the mechanisms of persuasion that operate through discourse. We present the Strategic…