Skip to content

Fix quickstart: correct agent_data placement and add model adapter implementation #70

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cemde merged 1 commit into from
Oct 6, 2026
Merged

Fix quickstart: correct agent_data placement and add model adapter implementation #70

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 14 additions & 8 deletions docs/getting-started/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,18 +171,24 @@ MASEval includes pre-built benchmarks for established evaluation suites. See the
**Using a default agent:** For quick evaluation or baseline comparisons, use the default benchmark class directly:

```python
from openai import OpenAI
from maseval.benchmark.tau2 import (
DefaultAgentTau2Benchmark, load_tasks, ensure_data_exists,
DefaultAgentTau2Benchmark, load_tasks, ensure_data_exists, configure_model_ids,
)
from maseval.interface.inference.openai import OpenAIModelAdapter

client = OpenAI()

class MyTau2Benchmark(DefaultAgentTau2Benchmark):
def get_model_adapter(self, model_id, **kwargs):
return OpenAIModelAdapter(client=client, model_id=model_id)

ensure_data_exists(domain="retail")
tasks = load_tasks("retail", split="base", limit=5)
configure_model_ids(tasks, user_model_id="gpt-4o")

benchmark = DefaultAgentTau2Benchmark(
agent_data={"model_id": "gpt-4o"},
n_task_repeats=4,
)
results = benchmark.run(tasks)
benchmark = MyTau2Benchmark(n_task_repeats=4)
results = benchmark.run(tasks, agent_data={"model_id": "gpt-4o"})
```

**Plugging in your own agent:** Subclass the base benchmark to use your own agent implementation:
Expand All @@ -196,8 +202,8 @@ class MyTau2Benchmark(Tau2Benchmark):
# Create your agent with these tools
...

benchmark = MyTau2Benchmark(agent_data={}, n_task_repeats=4)
results = benchmark.run(tasks)
benchmark = MyTau2Benchmark(n_task_repeats=4)
results = benchmark.run(tasks, agent_data={})
```

The base class handles environment setup, user simulation, and evaluation—you only implement `setup_agents()` and `run_agents()`.
Expand Down
Loading