fix readme (#862)

Co-authored-by: alcholiclg <ligongshengzju@foxmail.com>

Author: alcholiclg

README.md

@@ -54,6 +54,9 @@ MS-Agent is a lightweight framework designed to empower agents with autonomous e
 
 ## 🎉 News
 
+* 🚀 Feb 06, 2026: Release MS-Agent v1.6.0rc1, which includes the following updates:
+  - **Agentic Insight v2**: A fully refactored deep-research system with better performance, scalability, and trustworthiness, now available in WebUI. See [Agentic Insight v2](https://github.com/modelscope/ms-agent/tree/main/projects/deep_research/v2).
+
 * 🚀 Feb 04, 2026: Release MS-Agent v1.6.0rc0, which includes the following updates:
   - **Code Genesis** for complex code generation tasks, refer to [Code Genesis](https://github.com/modelscope/ms-agent/tree/main/projects/code_genesis)
   - **Singularity Cinema** for animated video generation workflow, refactored version, refer to [Singularity Cinema](https://github.com/modelscope/ms-agent/tree/main/projects/singularity_cinema)
@@ -352,6 +355,16 @@ This project provides a framework for **Deep Research**, enabling agents to auto
 
 - **Lightweight & Efficient** - Support "search-then-execute" mode, completing complex research tasks within few minutes, significantly reducing token consumption.
 
+#### 🚀 Agentic Insight v2 (Recommended)
+
+- **Performance**: Multi-model orchestration (a low-cost combo across qwen3-max/plus/flash) achieves **49.94** on DeepResearch Bench.
+- **Deep Agents architecture**: "Researcher + tool-augmented sub-agents (Searcher/Reporter)" for flexible task allocation and efficient concurrency.
+- **File system as context**: Structured artifacts persisted to disk for low-loss context handoff and stable long-horizon runs (resume-friendly).
+- **Evidence-driven writing**: Reports are grounded in an indexed evidence base, improving trustworthiness and traceability.
+- **Deep-research toolchain**: Decoupled modules like todo list / evidence store / report generator for reuse and extensibility.
+
+See [Agentic Insight v2](projects/deep_research/v2/README.md).
+
 
 #### 📺 Demonstration
 

README_ZH.md

@@ -51,6 +51,9 @@ MS-Agent是一个轻量级框架，旨在为智能体提供自主探索能力。
 
 ## 🎉 新闻
 
+* 🚀 **2026年2月6日：发布 MS-Agent v1.6.0rc1，主要更新内容如下：**
+  - **Agentic Insight v2**：完整重构的深度研究系统，性能更优、可扩展性更强、可信度更高，支持在webui中使用，详情请参考 [Agentic Insight v2](https://github.com/modelscope/ms-agent/tree/main/projects/deep_research/v2)
+
 * 🚀 **2026年2月4日：发布 MS-Agent v1.6.0rc0，主要更新内容如下：**
   - **Code Genesis**：针对复杂代码生成任务的专项功能，详情请参考 [Code Genesis](https://github.com/modelscope/ms-agent/tree/main/projects/code_genesis)
   - **Singularity Cinema**：动画视频生成工作流的重构版本，详情请参考 [Singularity Cinema](https://github.com/modelscope/ms-agent/tree/main/projects/singularity_cinema)
@@ -323,6 +326,16 @@ asyncio.run(main())
 
 - **轻量级与高效** - 支持"搜索后执行"模式，在几分钟内完成复杂的研究任务，显著减少token消耗。
 
+#### 🚀 Agentic Insight v2（推荐）
+
+- **性能表现** - 基于 qwen3-max/plus/flash 多模型协同（低成本组合），在 DeepResearch Bench 上取得 **49.94** 分，性能位于同类框架一线水平
+- **Deep Agents 架构** - "Researcher + 工具化子 Agent（Searcher/Reporter）"模式，支持任务灵活分配与高效并发
+- **文件系统即上下文** - 中间产物结构化存储到文件系统，实现低损耗上下文传递和长链路任务稳定运行
+- **证据驱动写作** - 自主建立带索引的证据库，报告以证据为唯一事实基础，实现报告高可信度与来源可追溯
+- **深度研究专用工具链** - 提供 todo_list / evidence_store / report_generator 等专用模块，实现核心能力的解耦与高度复用
+
+使用方式请参考 [Agentic Insight v2](projects/deep_research/v2/README.md)。
+
 #### 📺 演示
 
 以下是Agentic Insight框架的实际演示，展示了其在高效处理复杂研究任务方面的能力。

projects/deep_research/v2/README.md

@@ -59,6 +59,21 @@ PYTHONPATH=. python ms_agent/cli/cli.py run \
   --output_dir "output/deep_research/runs"
 ```
 
+#### Run in WebUI
+
+You can also use Agentic Insight v2 from the built-in WebUI:
+
+```bash
+ms-agent ui
+```
+
+Then open `http://localhost:7860`, select **Deep Research**, and make sure you have configured:
+
+- `OPENAI_API_KEY` / `OPENAI_BASE_URL` (LLM settings)
+- Either `EXA_API_KEY` or `SERPAPI_API_KEY` (search tools)
+
+You can set them via `.env` or in WebUI **Settings**. WebUI run artifacts are stored under `webui/work_dir/<session_id>/`.
+
 ### Key configs (what to edit)
 
 - `projects/deep_research/v2/researcher.yaml`

projects/deep_research/v2/README_zh.md

@@ -59,6 +59,21 @@ PYTHONPATH=. python ms_agent/cli/cli.py run \
   --output_dir "output/deep_research/runs"
 ```
 
+#### 在 WebUI 中使用
+
+你也可以在内置 WebUI 中使用 Agentic Insight v2：
+
+```bash
+ms-agent ui
+```
+
+然后打开 `http://localhost:7860`，选择 **Deep Research**，并确保已配置：
+
+- `OPENAI_API_KEY` / `OPENAI_BASE_URL`（LLM 配置）
+- 二选一：`EXA_API_KEY` 或 `SERPAPI_API_KEY`（搜索工具）
+
+你可以通过 `.env` 或 WebUI 的 **Settings** 进行配置。WebUI 的运行产物会保存在 `webui/work_dir/<session_id>/` 下。
+
 ### 关键配置（常改位置）
 
 - `projects/deep_research/v2/researcher.yaml`