On ALFWorld, FlowEvo achieves an 82.8% success rate, 23.6 percentage points above the strongest baseline...
正在加载行业信息...
正在加载行业信息...
开源项目
更新于 2026/7/28 17:22:17
A training-free framework for self-evolving LLM agents that co-evolves workflows and executable skills via workflow-to-skill compilation, skill-to-workflow feedback, and skill curation.
On ALFWorld, FlowEvo achieves an 82.8% success rate, 23.6 percentage points above the strongest baseline...
Experiments on benchmarks spanning interactive environments (ALFWorld) and code/math generation (HumanEval, GSM8K)...
Experiments on benchmarks spanning interactive environments (ALFWorld) and code/math generation (HumanEval, GSM8K)...
The code is public at https://github.com/DEFENSE-SEU/FlowEvo.
暂无来源链接。