gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 15:37:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: enhance feedback handling in MultiProcessEvolvingStrategy for improved task evolution (#1274)

Browse Source
This commit is contained in:
Xu Yang
2025-10-23 16:00:23 +08:00
committed by GitHub
parent 03f22dc7c7
commit afb575cc91
2 changed files with 27 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+17 -16
View File
@@ -413,16 +413,16 @@ More documents can be found in the **[📖 readthedocs](https://rdagent.readthed
# 📃 Paper/Work list
## Overall Technical Report
- [R&D-Agent: Automating Data-Driven AI Solution Building Through LLM-Powered Automated Research, Development, and Evolution](https://arxiv.org/abs/2505.14738)
- [R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science](https://arxiv.org/abs/2505.14738)
```BibTeX
@misc{yang2024rdagent,
title={R\&D-Agent: Automating Data-Driven AI Solution Building Through LLM-Powered Automated Research, Development, and Evolution},
author={Xu Yang and Xiao Yang and Shikai Fang and Bowen Xian and Yuante Li and Jian Wang and Minrui Xu and Haoran Pan and Xinpeng Hong and Weiqing Liu and Yelong Shen and Weizhu Chen and Jiang Bian},
year={2025},
eprint={2505.14738},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2505.14738}
@misc{yang2025rdagentllmagentframeworkautonomous,
title={R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science},
author={Xu Yang and Xiao Yang and Shikai Fang and Yifei Zhang and Jian Wang and Bowen Xian and Qizheng Li and Jingyuan Li and Minrui Xu and Yuante Li and Haoran Pan and Yuge Zhang and Weiqing Liu and Yelong Shen and Weizhu Chen and Jiang Bian},
year={2025},
eprint={2505.14738},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2505.14738},
}
```
![image](https://github.com/user-attachments/assets/28b0488d-a546-4fef-8dc5-563ed64a9b4d)
@@ -468,13 +468,14 @@ For more detail, please refer to our **[🖥️ Live Demo page](https://rdagent.
- [R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization](https://arxiv.org/abs/2505.15155)
```BibTeX
@misc{li2025rdagentquant,
title={R\&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization},
author={Yuante Li and Xu Yang and Xiao Yang and Minrui Xu and Xisen Wang and Weiqing Liu and Jiang Bian},
year={2025},
eprint={2505.15155},
archivePrefix={arXiv},
primaryClass={cs.AI}
@misc{li2025rdagentquantmultiagentframeworkdatacentric,
title={R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization},
author={Yuante Li and Xu Yang and Xiao Yang and Minrui Xu and Xisen Wang and Weiqing Liu and Jiang Bian},
year={2025},
eprint={2505.15155},
archivePrefix={arXiv},
primaryClass={q-fin.CP},
url={https://arxiv.org/abs/2505.15155},
}
```
![image](https://github.com/user-attachments/assets/3186f67a-c2f8-4b6b-8bb9-a9b959c13866)
rdagent/components/coder/CoSTEER/evolving_strategy.py
+10 -6
View File
@@ -81,6 +81,11 @@ class MultiProcessEvolvingStrategy(EvolvingStrategy):
) -> EvolvingItem:
code_list = [None for _ in range(len(evo.sub_tasks))]
last_feedback = None
if len(evolving_trace) > 0:
last_feedback = evolving_trace[-1].feedback
assert isinstance(last_feedback, CoSTEERMultiFeedback)
# 1.找出需要evolve的task
to_be_finished_task_index: list[int] = []
for index, target_task in enumerate(evo.sub_tasks):
@@ -94,15 +99,14 @@ class MultiProcessEvolvingStrategy(EvolvingStrategy):
elif (
target_task_desc not in queried_knowledge.success_task_to_knowledge_dict
and target_task_desc not in queried_knowledge.failed_task_info_set
and not (self.improve_mode and last_feedback[index] is None)
and not (
self.improve_mode
and isinstance(last_feedback, CoSTEERMultiFeedback)
and last_feedback[index] is None
)
):
to_be_finished_task_index.append(index)
last_feedback = None
if len(evolving_trace) > 0:
last_feedback = evolving_trace[-1].feedback
assert isinstance(last_feedback, CoSTEERMultiFeedback)
result = multiprocessing_wrapper(
[
(