diff --git a/README.md b/README.md
index 14a8f4ce..7e852cba 100644
--- a/README.md
+++ b/README.md
@@ -285,7 +285,7 @@ Requirements / tips:
   - **Supervisor orchestrator**: fixed name **`orchestrator-supervisor.md`** (plus optional `orchestrator_instruction_supervisor`); requires at least one sub-agent.
   - **Sub-agents** (for **deep** / **supervisor**): other `*.md` files (YAML front matter + body). Not used as **`task`** targets if marked orchestrator-only.
 - **Management** – Web UI: **Agents → Agent management**; API `/api/multi-agent/markdown-agents`.
-- **Config** – `multi_agent` in `config.yaml`: `enabled`, `default_mode`, `robot_use_multi_agent`, `batch_use_multi_agent`, `max_iteration`, `plan_execute_loop_max_iterations`, per-mode orchestrator instruction fields, optional YAML `sub_agents` merged with disk (`id` clash → Markdown wins), **`eino_skills`**, **`eino_middleware`** (optional ADK middleware and Deep/Supervisor tuning).
+- **Config** – `multi_agent` in `config.yaml`: `enabled`, `robot_default_agent_mode`, `batch_use_multi_agent`, `max_iteration`, `plan_execute_loop_max_iterations`, per-mode orchestrator instruction fields, optional YAML `sub_agents` merged with disk (`id` clash → Markdown wins), **`eino_skills`**, **`eino_middleware`** (optional ADK middleware and Deep/Supervisor tuning).
 - **Details** – **[docs/MULTI_AGENT_EINO.md](docs/MULTI_AGENT_EINO.md)** (streaming, robots, batch, middleware caveats).
 
 ### Skills System (Agent Skills + Eino)
@@ -536,7 +536,7 @@ agents_dir: "agents"  # Multi-agent Markdown definitions (orchestrator + sub-age
 multi_agent:
   enabled: false
   default_mode: "single"   # single | multi (UI default when multi-agent is enabled)
-  robot_use_multi_agent: false
+  robot_default_agent_mode: react
   batch_use_multi_agent: false
   orchestrator_instruction: ""  # Deep; used when orchestrator.md body is empty
   # orchestrator_instruction_plan_execute / orchestrator_instruction_supervisor optional
diff --git a/README_CN.md b/README_CN.md
index db2d00c6..6ba2a1d4 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -283,7 +283,7 @@ go build -o cyberstrike-ai cmd/server/main.go
   - **Supervisor 主代理**：固定 **`orchestrator-supervisor.md`**（另可配 `orchestrator_instruction_supervisor`）；至少需一名子代理。
   - **子代理**（**deep** / **supervisor**）：其余 `*.md`；标成 orchestrator 的不会进入 `task` 列表。
 - **界面管理**：**Agents → Agent 管理**；API `/api/multi-agent/markdown-agents`。
-- **配置项**：`multi_agent`：`enabled`、`default_mode`、`robot_use_multi_agent`、`batch_use_multi_agent`、`max_iteration`、`plan_execute_loop_max_iterations`、各模式 orchestrator 指令字段、可选 YAML `sub_agents` 与目录合并（同 `id` → Markdown 优先）、**`eino_skills`**、**`eino_middleware`**。
+- **配置项**：`multi_agent`：`enabled`、`robot_default_agent_mode`、`batch_use_multi_agent`、`max_iteration`、`plan_execute_loop_max_iterations`、各模式 orchestrator 指令字段、可选 YAML `sub_agents` 与目录合并（同 `id` → Markdown 优先）、**`eino_skills`**、**`eino_middleware`**。
 - **更多细节**：[docs/MULTI_AGENT_EINO.md](docs/MULTI_AGENT_EINO.md)（流式、机器人、批量、中间件差异）。
 
 ### Skills 技能系统（Agent Skills + Eino）
@@ -534,7 +534,7 @@ agents_dir: "agents"  # 多代理 Markdown（主代理 orchestrator.md + 子代
 multi_agent:
   enabled: false
   default_mode: "single"   # single | multi（开启多代理时的界面默认模式）
-  robot_use_multi_agent: false
+  robot_default_agent_mode: react
   batch_use_multi_agent: false
   orchestrator_instruction: ""  # Deep；orchestrator.md 正文为空时使用
   # orchestrator_instruction_plan_execute / orchestrator_instruction_supervisor 可选