Shaokun Zhang
Shaokun Zhang
- [ ] Implement OPE CS with reward range robustness in VW - [ ] make default of automl to use these upper_bounds and lower_bound
## Why are these changes needed? We plan to support lexicographic optimization in BlendSearch. This pull request is primarily intended to track the implementation progress. We encourage everyone to provide...
## Why are these changes needed? AgentOptimizer, a new class for training AutoGen agents in the era of LLMs as a service. AgentOptimizer is able to prompt autogen agents to...
## Why are these changes needed? Update AgentOptimizer BibTeX. ## Related issue number ## Checks - [x] I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and...
## Why are these changes needed? This PR provides a basic implementation for SWE_bench benchmark (https://www.swebench.com). This PR is still on working and not ready for review. - [ ]...