SAGE Benchmark Agent
Configuration-driven experiment framework for evaluating agent capabilities.
Features
- Tool Selection Evaluation: Tool retrieval and ranking benchmarks
- Planning Evaluation: Multi-step planning with tool composition
- Timing Detection: Timing judgment for tool invocation decisions
Quick Start
# Install
pip install isage-benchmark-agent
# Run tool selection experiment
sage-agent-bench tool-selection --config config/tool_selection_exp.yaml
# Run planning experiment
sage-agent-bench planning --config config/planning_exp.yaml
Documentation
See benchmark_agent/README.md for detailed documentation.
Development
# Clone
git clone https://github.com/intellistream/sage-agent-benchmark.git
cd sage-agent-benchmark
# Setup virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install in development mode
pip install -e ".[dev]"
# Run tests
pytest
License
MIT License - see LICENSE for details.
Metadata
Release files for isage-benchmark-agent 0.1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| isage_benchmark_agent-0.1.0.1.tar.gz | 273.7 kB | Details |
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| isage_benchmark_agent-0.1.0.1-py2.py3-none-any.whl | Python 2, Python 3 | none | any | Details |
| isage_benchmark_agent-0.1.0.1-cp311-none-any.whl | CPython 3.11 | none | any | Details |
Total release size: 725.0 kB
Release files / isage_benchmark_agent-0.1.0.1.tar.gz
| Download URL | isage_benchmark_agent-0.1.0.1.tar.gz |
|---|---|
| Size | 273.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e9d681ddf8311852c3f8257521496898f2ab1d45460fff6d2676f8cc42e4f3d1
|
|
BLAKE2b-256 checksum How to use checksums |
aa973108af8eff75c0426e52ca5dae5d1135082bce81430ba09d502606df48b2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.11
|
Release files / isage_benchmark_agent-0.1.0.1-py2.py3-none-any.whl
| Download URL | isage_benchmark_agent-0.1.0.1-py2.py3-none-any.whl |
|---|---|
| Size | 306.9 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
c2f37f3611eb676473cc3d4f4a2f29f5a86d0299c700d0f4381299e2edfb8c6f
|
|
BLAKE2b-256 checksum How to use checksums |
264aa2b2f99a70c2e7906d4213125e5b6362c805ef2a1d33831c44da6db01add
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.11
|
Release files / isage_benchmark_agent-0.1.0.1-cp311-none-any.whl
| Download URL | isage_benchmark_agent-0.1.0.1-cp311-none-any.whl |
|---|---|
| Size | 144.4 kB |
| Tags | CPython 3.11 |
|
SHA-256 checksum How to use checksums |
dc66c241f08b78811244d71d1776b1c0e47af5aa9780bb0837268cd05b9ccd8d
|
|
BLAKE2b-256 checksum How to use checksums |
a1fc742f92ba9af37bae6074a47546fff7db7b8d5e61dd65dc02a0410ddbaa34
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
