Noah Shinn — accepted AI-conference papers

2025

{$\tau$}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World Domains

Shunyu Yao, Noah Shinn, Pedram Razavi, Karthik R Narasimhan

ICLR 2025poster

Existing benchmarks for language agents do not set them up to interact with human users or follow domain-specific rules, both of which are vital to safe and realistic deployment. We propose $\tau$-bench, a benchmark with two domains (retail and airline) emulating dynamic conversations between a user…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Reflexion: language agents with verbal reinforcement learning

Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik R Narasimhan, Shunyu Yao

NeurIPS 2023poster

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning…

Cited by 1443 Source ↗PDF ↗code ↗Scholar ↗