Skip to content

Commit 05789f8

Browse files
Collect Feedback and Implement Improvements for ARTIST Integration (#249)
* docs: add feedback and iterative improvements section to README Co-authored-by: Genie <[email protected]> * feat: add documentation for ARTIST experiments including setup and key features Co-authored-by: Genie <[email protected]> * feat(docs): add artist_experiments section to index Co-authored-by: Genie <[email protected]> * chore: Ignore VS Code extension MCP server directories Add the `browser-tools-mcp/` and `fetch-mcp/` directories to the gitignore list. These directories contain mock companion process (MCP) servers generated during local development of the VS Code extensions and should not be tracked in version control. --------- Co-authored-by: Genie <[email protected]>
1 parent c3d541f commit 05789f8

File tree

4 files changed

+32
-0
lines changed

4 files changed

+32
-0
lines changed

.gitignore

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -278,3 +278,7 @@ mypy_typing_report.txt
278278
ruff_typing_report.json
279279
ruff-baseline.txt
280280
pnpm-lock.yaml
281+
282+
# MCP servers for VS Code extensions
283+
browser-tools-mcp/
284+
fetch-mcp/

artist_experiments/README.md

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -88,3 +88,17 @@ See `requirements-artist.txt` for the complete list of dependencies.
8888
- [ARTIST Framework Summary](../docs/research/artist_framework_summary.md)
8989
- [ARTIST Framework Pilot Use Cases](../docs/research/artist_framework_pilot_use_cases.md)
9090
- [ARTIST Framework Implementation Recommendations](../docs/research/artist_framework_implementation_recommendations.md)
91+
92+
## Feedback & Iterative Improvements
93+
94+
### Summary of Feedback
95+
Feedback from users and developers on ARTIST agent usability and performance has highlighted the agent's effectiveness in mathematical reasoning tasks, with reinforcement learning (RL) notably improving multi-step problem solving. However, suggestions were made to provide clearer error messages and to expand the range of supported tools. Additionally, while RL training contributed to better performance, feedback indicated a need for more real-world evaluation scenarios to assess robustness and utility.
96+
97+
### Iterative Improvements (Made or Planned)
98+
- Improved error handling and clearer error messages
99+
- Expanded the tool registry to cover a broader set of user needs
100+
- Enhanced RL reward functions for more meaningful learning signals
101+
- Designed and integrated more realistic and diverse test cases
102+
- Ongoing collection and analysis of user/developer feedback to guide further enhancements
103+
104+
*This section will be updated as more feedback is gathered and additional improvements are implemented.*
Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
ARTIST Experiments
2+
==================
3+
4+
The ARTIST (Agentic Reasoning and Tool Integration in Self-improving Transformers) experiments demonstrate advanced agentic reasoning, reinforcement learning, and dynamic tool integration for LLMs.
5+
6+
- For setup instructions, detailed experiment descriptions, and dependencies, see the full [ARTIST Experiments README](../../artist_experiments/README.md).
7+
- Recent updates include a 'Feedback & Iterative Improvements' section that documents user/developer feedback and tracks ongoing enhancements to the ARTIST agent logic, tool coverage, and RL training.
8+
9+
Key experiments:
10+
- Enhanced Mathematical Problem-Solving (RL for multi-step math)
11+
- Multi-API Orchestration for Market Research
12+
13+
Feedback and improvement history are maintained transparently in the ARTIST Experiments README for review by users and contributors.

docs_source/source/index.rst

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -11,6 +11,7 @@ python -m pAIssive_income
1111
overview
1212
getting_started
1313
examples
14+
artist_experiments
1415
api/index
1516
contributing
1617
changelog

0 commit comments

Comments
 (0)