Skip to content

fix(examples/tau-bench): use RunConfig.agent_strategy in TAU_CONFIGS (slime #2101) #280

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
aoshen02 merged 1 commit into from
Jun 23, 2026
Merged

fix(examples/tau-bench): use RunConfig.agent_strategy in TAU_CONFIGS (slime #2101) #280

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion examples/tau-bench/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ You need to configure your litellm API in generate_with_tau.py for user simulati

TAU_CONFIGS = {
"env": "retail", # Select between ["retail", "airline"]
"agent": "tool-calling", # Select between ["tool-calling", "act", "react", "few-shot"], only tool-calling implemented for now
"agent_strategy": "tool-calling", # Select between ["tool-calling", "act", "react", "few-shot"], only tool-calling implemented for now
"user_model": "gemini-2.0-flash-lite", # Cheap Model for user simulator
"user_model_provider": "gemini",
"task_split": "train", # Select between ["train", "test", "dev"] for retail, ["test"] for airline
Expand Down
4 changes: 2 additions & 2 deletions examples/tau-bench/generate_with_tau.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
# Agent rollout uses vLLM; only user_model / user_model_provider affect the user simulator here.
TAU_CONFIGS = {
"env": "retail", # Select between ["retail", "airline"]
"agent": "tool-calling", # Select between ["tool-calling", "act", "react", "few-shot"]
"agent_strategy": "tool-calling", # Select between ["tool-calling", "act", "react", "few-shot"]
# Default: local vLLM user sim (no external API). For Gemini API user sim, switch to:
# "user_model": "gemini-2.5-flash-lite", "user_model_provider": "gemini",
"user_model": "openai/local-qwen3-4b",
Expand Down Expand Up @@ -69,7 +69,7 @@ def resolve_tau_config(args: Any) -> RunConfig:

return RunConfig(
env=tau_config.env,
agent=tau_config.agent,
agent_strategy=tau_config.agent_strategy,
user_model=user_model,
user_model_provider=user_model_provider,
task_split=tau_config.task_split,
Expand Down