From ae399ecbc4eb7f621ff27bb9b39760ad4be8dee8 Mon Sep 17 00:00:00 2001
From: langfeng <langfeng.cs@gmail.com>
Date: Sat, 26 Sep 2026 12:25:16 +0800
Subject: [PATCH] Rename framework image and update README links

---
 README.md                                           |   4 ++--
 .../{drmas_framework.png => drmas_framework_v2.png} | Bin
 2 files changed, 2 insertions(+), 2 deletions(-)
 rename docs/drmas/{drmas_framework.png => drmas_framework_v2.png} (100%)

diff --git a/README.md b/README.md
index 210b161..096ff76 100644
--- a/README.md
+++ b/README.md
@@ -50,8 +50,8 @@ Dr. MAS is designed for **end-to-end post-training** of **Multi-Agent LLM System
 This framework features **flexible agent registry**, **customizable multi-agent orchestration**, **LLM sharing/non-sharing (e.g., heterogeneous LLMs)**, **per-agent configuration**, and **shared resource pooling**, making it well suited for training multi-agent LLM systems with RL.
 
 <p align="center">
-    <a href="./docs/drmas/drmas_framework.png">
-        <img src="./docs/drmas/drmas_framework.png" alt="Figure 2: The Dr. MAS framework connects environment workers, multi-agent orchestration, agent-model assignment, shared GPU scheduling, and per-worker-group optimization." width="100%">
+    <a href="./docs/drmas/drmas_framework_v2.png">
+        <img src="./docs/drmas/drmas_framework_v2.png" alt="Figure 2: The Dr. MAS framework connects environment workers, multi-agent orchestration, agent-model assignment, shared GPU scheduling, and per-worker-group optimization." width="100%">
     </a>
     <br>
     <em>Figure 2. The Dr. MAS framework for end-to-end multi-agent LLM RL.</em>
diff --git a/docs/drmas/drmas_framework.png b/docs/drmas/drmas_framework_v2.png
similarity index 100%
rename from docs/drmas/drmas_framework.png
rename to docs/drmas/drmas_framework_v2.png