AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce Ecologically Rational Meta-learned Inference (ERMI), a computational framework combining large language models with meta-learning to model human cognition as adaptive optimization to real-world environments. The approach successfully predicts human behavior across 15 experiments in function learning, category learning, and decision-making, suggesting human cognition reflects principled adaptation to ecological statistical structures.
AINeutralarXiv – CS AI · Jun 96/10
🧠RunAgent has developed SuperBrowser, an autonomous web navigation agent that mimics human browsing behavior through selective perception and structured memory management. The system achieves 89.47% success on the Mind2Web Hard benchmark, outperforming all published open-source baselines by applying consistent cognitive principles throughout its architecture.
AINeutralarXiv – CS AI · Jun 45/10
🧠Researchers introduce ChessMimic, a system of three transformer models that predict human chess moves, thinking time, and game outcomes in online blitz chess with rating-specific calibration. The models outperform existing systems like Maia across multiple performance metrics while using significantly fewer parameters, with code and weights publicly released.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers propose a biologically-inspired approach to safety thresholds in autonomous driving by modeling Surrogate Safety Measures (SSMs) as leaky integrate-and-fire neuron spiking thresholds within a spiking neural network. Trained on human braking data from controlled experiments, the SNN captures dynamic safety responses that fixed thresholds miss, potentially bridging the gap between objective risk metrics and subjective human perception.
AINeutralarXiv – CS AI · May 276/10
🧠Research comparing 120 base and aligned language model pairs reveals that alignment training makes models more normative but less descriptive of actual human behavior. Base models predict real human choices in multi-round strategic games 10 times better, while aligned models excel only in single-shot, textbook scenarios where human behavior follows rational expectations.
AINeutralarXiv – CS AI · Apr 146/10
🧠Researchers introduce SimBench, a standardized benchmark for evaluating how faithfully large language models simulate human behavior across 20 diverse datasets. The study reveals current LLMs achieve only modest simulation fidelity (40.80/100) and uncovers critical limitations including an alignment-simulation tradeoff and struggles with demographic-specific behavior replication.
AIBearisharXiv – CS AI · Apr 136/10
🧠Researchers introduce OmniBehavior, a benchmark for evaluating large language models' ability to simulate real-world human behavior across complex, long-horizon scenarios. The study reveals that current LLMs struggle with authentic behavioral simulation and exhibit systematic biases toward homogenized, overly-positive personas rather than capturing individual differences and realistic long-tail behaviors.
AINeutralarXiv – CS AI · Apr 106/10
🧠A research study analyzes six leading large language models to identify shared cultural patterns revealed in their training data, finding consensus around themes like narrative meaning-making, status competition, and moral rationalization. The findings suggest LLMs function as 'cultural condensates' that compress how humans describe and contest their social lives across massive text datasets.
