tau2

Here are 5 public repositories matching this topic...

This fork of tau2-bench investigates whether LLM agent performance varies based on the temporal context of dates in prompts.

benchmark agents llm tau2

A2A-compatible Green Agent that runs τ²-bench end-to-end on AgentBeats

docker benchmark uv a2a tau2 agentbeats

Trajectory analysis framework for agent evaluation — moving beyond reward scores to behavioral explanation.

OpenEuroLLM tau2-bench evaluation harness with OLMo and Qwen serving, user-simulator, and aggregation scripts.

evaluation tool-use function-calling olmo tau2

Reproducible tau2-SEA dataset generation pipeline using the official DeepSeek API

To associate your repository with the tau2 topic, visit your repo's landing page and select "manage topics."