OSCToM: RL-Guided Adversarial Generation for High-Order Theory of Mind
arXiv cs.AI·Sharmin Sultana Srishty, Kazi Mahathir Rahman, Malaika Parizat Sakkhi, Samia Shahid Prianna, Shaikhul Islam Sinat
15h agoQuick Take
OSCToM enhances Theory of Mind reasoning in LLMs through RL-guided adversarial generation.
Key Points
- Models nested belief conflicts in LLM tasks.
- Achieves 76% accuracy on FANToM benchmark.
- Code available on GitHub for further research.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →3d ago
FeaturedOriginal
From Prompts to Protocols: An AI Agent for Laboratory Automation
AI Summary
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.