# SelfEvolvingAgent

**Repository Path**: mirrors_Tencent/SelfEvolvingAgent

## Basic Information

- **Project Name**: SelfEvolvingAgent
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-06-13
- **Last Updated**: 2026-03-29

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Tencent AI LAB - Self-Improving Agent

<p align="center"><img src="logo.png" alt="" width="50%"/></p>

We present the code of our academic papers of self-evolving agent:

- `WebEvolver`: [WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model](https://arxiv.org/abs/2504.21024), EMNLP 2025
- `WebCoT`: [WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback](https://arxiv.org/abs/2505.20013), Findings of EMNLP 2025.
- `VScan`: [VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models](https://arxiv.org/abs/2505.22654), TMLR 2026

### Friendly links to follow-up works:

- [Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training](https://github.com/Tencent/CognitiveKernel-Pro).