Update README.md

README.md

@@ -1,10 +1,31 @@
 ---
 title: README
-emoji: 🦀
+emoji: ⚡
 colorFrom: blue
 colorTo: indigo
 sdk: static
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# Oxford Reasoning and Machine Learning Lab
+
+We conduct research on **AI evaluation, safety, and human–AI interaction** to advance understanding of how large language models reason, solve complex problems, and collaborate with humans.
+
+Our work combines **theoretical rigour** with **empirical investigation** to study how large language models process information, perform tasks, and behave in real-world settings.
+
+## Research Areas
+
+### Benchmarks and Evaluation
+We study the science of LLM evaluation, using **systematic reviews**, **benchmark analysis**, and **statistical modelling** to examine the validity of existing evaluation practices. We develop new benchmarks and evaluation frameworks to test the limits of LLM reasoning, especially in **adversarial**, **interactive**, and **low-resource language** settings.
+
+### Agentic AI for Science
+We build agentic AI systems that automate and augment key stages of the scientific process, including **literature discovery**, **evidence synthesis**, **hypothesis generation**, and **decision support**. A central focus is developing agents that are **reliable**, **transparent**, and **grounded in domain expertise** for real-world scientific and policy applications.
+
+### AI Safety
+We investigate the risks that advanced AI systems may pose to individuals and society. Our work spans the spectrum of harms, from **bias and toxicity in language models** to **misalignment in agentic systems**, alongside technical methods for mitigation and research on AI governance.
+
+### Human–AI Interaction
+We conduct large-scale empirical studies of how people use and respond to AI systems in decision-making contexts. This includes our landmark study of **1,300 participants** examining the use of LLMs in **medical self-diagnosis** and healthcare-related decision support.
+
+## Links
+- Website: [oxrml.com](https://oxrml.com/)