diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/gb200-fp4/agentic/agg-tp4-vllm-simple-agentic.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/gb200-fp4/agentic/agg-tp4-vllm-simple-agentic.yaml
index 41a1835083..3536914f92 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/gb200-fp4/agentic/agg-tp4-vllm-simple-agentic.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/minimax-m3/gb200-fp4/agentic/agg-tp4-vllm-simple-agentic.yaml
@@ -39,6 +39,9 @@ backend:
   connector: null
   kv_events_config: { aggregated: true }
   aggregated_environment:
+    HF_HUB_CACHE: "/hf_hub_cache"
+    HUGGINGFACE_HUB_CACHE: "/hf_hub_cache"
+    TRANSFORMERS_CACHE: "/hf_hub_cache"
     VLLM_ENGINE_READY_TIMEOUT_S: "7200"
     VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS: "1800"
     VLLM_FLOAT32_MATMUL_PRECISION: "high"
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 4eb0a2caa6..8e6c32b6f4 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -6821,3 +6821,13 @@
   description:
     - "Refresh to collect TensorRT-LLM server metrics."
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2774
+
+- config-keys:
+    - minimaxm3-fp4-gb200-dynamo-vllm-agentic-agg-mtp
+  scenario-type:
+    - agentic-coding
+  description:
+    - "Refresh the full GB200 aggregate Dynamo-vLLM AgentX configuration."
+    - "Use the mounted Hugging Face cache for the TP4 SimpleCPU-offload backend."
+    - "Use the committed MiniMax-M3 thinking-on EAGLE3-GQA acceptance target."
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2806