LLM agents can partially mimic human driving behaviors and decision ...
...Thirteen state-of-the-art LLMs from five families were evaluated, revealing notable differences in their ability to mimic human driving behavior....
https://www.sciencedirect.com/science/article/pii/S0968090X2600094X
Personality-Driven Decision-Making in LLM-Based Autonomous Agents
...Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents....
https://arxiv.org/abs/2504.00727
GitHub - tearcloud/Awesome-LM-AD-Decision: A comprehensive list of ...
...LLMs are primarily leveraged for their reasoning, planning, and natural language understanding/generation capabilities to guide autonomous driving decisions. A dominant trend in this area is the hybridization or agentic use of LLMs....
https://github.com/tearcloud/Awesome-LM-AD-Decision
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents ...
...The main decision drivers were whether the evidence goes beyond before-and-after observations into temporal and causal mechanisms, whether safety decay is confounded by general capability degradation, and whether mitigation and evaluation reliability are supported with concrete experiments....
https://openreview.net/forum?id=Fd1jgQQW28
Evaluation of Large Language Models for Decision Making in Autonomous ...
...This study aims to quantitatively assess the accuracy of spatial-aware decision-making in autonomous driving, using different LLMs, when provided with information about the coordinates and velocities of surrounding objects....
https://arxiv.org/pdf/2312.06351
Large Language Models as Decision Makers for Autonomous Driving
...This paper presents an initial step toward leveraging LLMs as effective decision-makers for intricate AD scenarios in terms of safety, efficiency, generalizability, and interoperability....
https://openreview.net/forum?id=NkYCuGM7E2
LLM-Driven Decision Support - emergentmind.com
...LLM-driven decision support is a framework integrating advanced language models with human oversight, ensuring transparent and auditable decision workflows. It applies to diverse fields like clinical diagnostics, logistics, and pricing, where hybrid human?AI interaction mitigates risks and reduces cognitive load. Techniques such as modular pipelines, Bayesian-inspired prompting, and ......
https://www.emergentmind.com/topics/llm-driven-decision-support
Dual-process theory and decision-making in large language models - Nature
...In this Review, we examine LLM outputs through the lens of dual-process theory and against the backdrop of human decision-making....
https://www.nature.com/articles/s44159-025-00506-1
GitHub - AIR-DISCOVER/Driving-Thinking-Dataset: decision-making ...
...This dataset aims to delve into the cognitive processes and decision-making mechanisms of drivers in real-world driving scenarios. By capturing authentic interactions and thought processes, it provides invaluable insights into human behavior, decision-making, and emotional responses during driving....
https://github.com/AIR-DISCOVER/Driving-Thinking-Dataset
Decision-Making Framework for Autonomous Vehicles in Complex ... - Springer
...Current behavior decision-making methods for autonomous vehicles often struggle to generalize to complex scenarios. Large language models (LLMs) offer a promising approach to address these limitations....
https://link.springer.com/article/10.1007/s42154-025-00408-1