diff --git a/.github/assets/wechat_group.jpeg b/.github/assets/wechat_group.jpeg
index 255e0d3..bc9a4dc 100644
Binary files a/.github/assets/wechat_group.jpeg and b/.github/assets/wechat_group.jpeg differ
diff --git a/README.md b/README.md
index cb3d7f4..e91ca6c 100644
--- a/README.md
+++ b/README.md
@@ -123,7 +123,7 @@ Moving beyond traditional human-in-the-loop systems, EvoScientist adopts a human
 > Looking for ready-to-use research skills? Check out [**EvoSkills**](https://github.com/EvoScientist/EvoSkills) — powered by [**EvoScientist**](https://github.com/EvoScientist/EvoScientist)'s engine and installable skills, the entire end-to-end research lifecycle is covered out of the box. [**EvoSkills**](https://github.com/EvoScientist/EvoSkills) are also compatible with other CLI coding agents.
 
 ## 🔥 News
-- **[03 Jun 2026]** 🥈 Ranked #2 on [ResearchClawBench](https://github.com/InternScience/ResearchClawBench) (Agent mode, as of 2026.6.3)! [**Leaderboard**](https://internscience.github.io/ResearchClawBench-Home/) 👈
+- **[03 Jun 2026]** 🥈 Ranked #2 overall — and 🥇 #1 among `GPT-5.4`-based agents — on [ResearchClawBench](https://github.com/InternScience/ResearchClawBench) (Agent Mode)! [**Leaderboard**](https://internscience.github.io/ResearchClawBench-Home/) 👈
 - **[18 Apr 2026]** 🥇 Ranked #1 on [DeepResearch Bench](https://deepresearch-bench.github.io/) at submission time! [**Leaderboard**](https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard) 👈
 - **[13 Apr 2026]** 🥇 Reclaimed #1 on [DeepResearch Bench II](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) at submission time! [**Leaderboard**](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) 👈
 - **[26 Mar 2026]** 🥇 Ranked #1 on [AstaBench Data Analysis](https://allenai-asta-bench-leaderboard.hf.space/home) at submission time! [**Leaderboard**](https://allenai-asta-bench-leaderboard.hf.space/data-analysis) 👈
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 554917a..3f29cdb 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -132,7 +132,7 @@ EvoScientist 超越了传统的人在回路（Human-in-the-Loop）模式，采
 
 ## 🔥 动态
 
-- **[2026 年 6 月 3 日]** 🥈 在 [ResearchClawBench](https://github.com/InternScience/ResearchClawBench) 排名第 2（Agent 模式，截止 2026.6.3）！[**排行榜**](https://internscience.github.io/ResearchClawBench-Home/) 👈
+- **[2026 年 6 月 3 日]** 在 [ResearchClawBench](https://github.com/InternScience/ResearchClawBench)（Agent 模式）中，🥈 总体排名第 2 —— 同时 🥇 在基于 `GPT-5.4` 的智能体中排名第 1！[**排行榜**](https://internscience.github.io/ResearchClawBench-Home/) 👈
 - **[2026 年 4 月 18 日]** 🥇 提交时在 [DeepResearch Bench](https://deepresearch-bench.github.io/) 排名第一！[**排行榜**](https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard) 👈
 - **[2026 年 4 月 13 日]** 🥇 再度登顶！提交时在 [DeepResearch Bench II](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) 重回第一！[**排行榜**](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) 👈
 - **[2026 年 3 月 26 日]** 🥇 提交时在 [AstaBench 数据分析](https://allenai-asta-bench-leaderboard.hf.space/home) 排名第一！[**排行榜**](https://allenai-asta-bench-leaderboard.hf.space/data-analysis) 👈