ReMe/benchmark/pibench/config/models/reme.yaml
imrewce 3924f89bb4
feat(bench): adding eval adapter for proactiveness on Pi-Bench (#439)
* feat(bench): adding eval adapter for proactiveness on Pi-Bench

* Revise README for π-Bench evaluation suite

Updated the README to reflect the new project name and description.

* fix(bench): refining pi-bench scripts according to cr comments

* fix(bench): restore agent builtin tools in prebuilt toolkit
2026-08-11 16:37:54 +08:00

40 lines
848 B
YAML

# ReMe model configuration for Pi-Bench
# Uses ReMe's AgentScope agent with Dashscope as the LLM backend
model:
model: reme
base_url: "http://localhost:8088"
api_key: "dummy"
provider: custom
max_tokens: 16384
max_tool_iterations: 120
memory_window: 100
user_agent:
model: qwen3.8-max
base_url: "${USER_BASE_URL}"
api_key: "${USER_API_KEY}"
temperature: 0.0
request_timeout: 360.0
judger:
model: qwen3.8-max
base_url: "${JUDGER_BASE_URL}"
api_key: "${JUDGER_API_KEY}"
temperature: 0.0
request_timeout: 360.0
tools:
brave_search_api_key: "${BRAVE_SEARCH_API_KEY}"
web_search_max_results: 10
nanobot:
trace_logs_dir: "~/.nanobot/trace_logs"
workspace_dir: "~/.nanobot/workspace"
copy_task_assets_to_workspace: true
run:
output_dir: outputs
log_level: INFO
user_mode: llm
turn_timeout: 2400.0