Mirco Musolesi

Moral Alignment for LLM Agents

2024 · arXiv (Cornell University)

Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are currently rather specialized, several research efforts are underway to develop more generalist …

DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation

2025 · arXiv (Cornell University)

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the most common strategies …

Opponent Shaping in LLM Agents

2025 · arXiv (Cornell University)

Large Language Models (LLMs) are increasingly being deployed as autonomous agents in real-world environments. As these deployments scale, multi-agent interactions become inevitable, making it essential to understand strategic behavior in such systems. A central open …