diff --git a/.gitea/workflows/autograde.yml b/.gitea/workflows/autograde.yml
index 1950d18..18beead 100644
--- a/.gitea/workflows/autograde.yml
+++ b/.gitea/workflows/autograde.yml
@@ -329,35 +329,31 @@ jobs:
       - name: Grade REPORT.md
         working-directory: ${{ github.workspace }}
         run: |
-          # LLM env vars are injected by Runner config (LLM_API_KEY, LLM_API_URL, LLM_MODEL)
-          if [ -f REPORT.md ] && [ -f .llm_rubrics/rubric_report.json ]; then
+          if [ -f REPORT.md ]; then
             python3 ./.autograde/llm_grade.py \
               --question "请评估这份后端与系统设计报告" \
               --answer REPORT.md \
-              --rubric .llm_rubrics/rubric_report.json \
               --out report_grade.json \
               --summary report_summary.md
             echo "✅ REPORT.md graded"
           else
             echo '{"total": 0, "flags": ["missing_file"]}' > report_grade.json
-            echo "⚠️ REPORT.md or rubric not found"
+            echo "⚠️ REPORT.md not found"
           fi
       
       - name: Grade FRONTEND.md
         working-directory: ${{ github.workspace }}
         run: |
-          # LLM env vars are injected by Runner config (LLM_API_KEY, LLM_API_URL, LLM_MODEL)
-          if [ -f FRONTEND.md ] && [ -f .llm_rubrics/rubric_frontend.json ]; then
+          if [ -f FRONTEND.md ]; then
             python3 ./.autograde/llm_grade.py \
               --question "请评估这份前端界面与交互设计报告" \
               --answer FRONTEND.md \
-              --rubric .llm_rubrics/rubric_frontend.json \
               --out frontend_grade.json \
               --summary frontend_summary.md
             echo "✅ FRONTEND.md graded"
           else
             echo '{"total": 0, "flags": ["missing_file"]}' > frontend_grade.json
-            echo "⚠️ FRONTEND.md or rubric not found"
+            echo "⚠️ FRONTEND.md not found"
           fi
       
       - name: Aggregate grades