Mingchen Zhuge

Adding a mechanism for self-improvement

1

## Summary of Updates 1️⃣ **Internal Feedback Action:** Added the _Feedback_ action in `metagpt/actions/internal_feedback.py` to allow internal evaluation among agents (currently supporting the handover process). 2️⃣ **Action Functions Enhancement:** Introduced...

Support Multimodal Input for Agents

18

Hi, @neubig @xingyaoww @li-boxuan or any brother who are interesting, I am currently preparing for [MLAgentBench](https://arxiv.org/abs/2310.03302) evaluation and supporting the [GAIA](https://huggingface.co/datasets/gaia-benchmark/GAIA) evaluation. @Jiayi-Pan, please see [GPTSwarm](https://github.com/metauto-ai/gptswarm), where these multimodal readers...

VideoLink

4

https://github.com/mczhuge/NLSOM/assets/64179323/62fb8500-6c22-4ed4-bf61-bc3bc0a843bb

**To the agents contributors**, I have read the Agent2.0 paper and I personally really like it. The new framework is a good one and we share many similar interests and...

**Dear Authors,** Thank you for sharing your work. Appreciate your contribution to the field. I’d like to bring your attention to a project that seems closely related to your research,...