James Zou

LLMs exhibit "Thinking Inertia," stubbornly continuing to show explicit reasoning even when explicitly instructed not to, particularly in open-ended tasks.

Collective dynamics of AI agents reveal surprising patterns: while communication boosts accuracy on objective tasks, it can lead to political bias in group opinions.

Conversational phase structures can be reliably observed in clinical encounters, but patient states are only partially recoverable, challenging assumptions about transcript-based inference.

Achieving up to 2,500x speed improvements, string2string Studio revolutionizes string-to-string analysis by making complex algorithms accessible and interactive in the browser.

Simulating 8.3 billion diverse personas reveals nuanced user interactions that traditional evaluations miss, transforming how we assess AI systems.

DeepDebug achieves a 32% improvement in task recovery accuracy, showcasing a powerful new approach to debugging LLM agent failures.

Voice AI systems can recognize emotional cues but consistently ignore them in decision-making, leading to dangerous misinterpretations.

Advanced Vision-Language-Action models can be dramatically compressed by up to 50% without losing performance, reshaping our approach to robotic manipulation.

Data2Story not only automates data journalism but also ensures every claim is traceable back to its source, revolutionizing trust in automated reporting.

Looping language models isn't just for single agents anymore: Recursive Multi-Agent Systems (RecursiveMAS) show that agent collaboration itself can be scaled through recursion, yielding faster and more efficient problem-solving.