Karthik R. Narasimhan
Associate Professor, Computer Science, Princeton (on sabbatical)
Head of Research, Sierra
I work on problems at the intersection of language and decision making. I like to build autonomous agents that learn to operate in the world using both their own experience and existing human knowledge.
I previously received my PhD from MIT, advised by Prof. Regina Barzilay, and spent a year as a visiting research scientist at OpenAI in 2017-18.
Research highlights
- Language models: GPT (2018)
- Language agents: Text-DQN (2015), CALM (2020), ReAct (2022), Tree of Thoughts (2023), Reflexion (2023), CoALA (2023), SWE-agent (2024)
- Datasets/Benchmarks: WebShop (2022), InterCode (2023), SWE-bench (2023), C-STS (2023), SILG (2021), TAU-bench (2024)
- Efficiency and Safety: DataMUX (2022), Toxicity in ChatGPT (2023)
- Reinforcement Learning: h-DQN (2016), Multi-Objective RL (2019), POLCO (2021), XTX (2022)
For more publications, please see my Google Scholar page.