diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-agentic.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-agentic.yaml
index 7dc3d4979..0c6bb858b 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-agentic.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-agentic.yaml
@@ -95,12 +95,12 @@ srun_options:
 
 benchmark:
   type: custom
-  aiperf_server_metrics: true
   command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh
   env:
     INFMAX_CONTAINER_WORKSPACE: "/infmax-workspace"
     AIPERF_TRACE_IDLE_GAP_CAP_SECONDS: "300"
     AIPERF_LIVE_FAILED_REQUEST_THRESHOLD: "0.25"
+    AIPERF_SERVER_METRICS_URLS: "http://localhost:8000/metrics"
     AIPERF_REQUIRED_SERVER_METRIC_PREFIX: "vllm:"
     RESULT_DIR: "/logs/agentic"
     PORT: "8000"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-eval-agentic.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-eval-agentic.yaml
index f56268252..05bf13002 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-eval-agentic.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-eval-agentic.yaml
@@ -93,12 +93,12 @@ srun_options:
 
 benchmark:
   type: custom
-  aiperf_server_metrics: true
   command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh
   env:
     INFMAX_CONTAINER_WORKSPACE: "/infmax-workspace"
     AIPERF_TRACE_IDLE_GAP_CAP_SECONDS: "300"
     AIPERF_LIVE_FAILED_REQUEST_THRESHOLD: "0.25"
+    AIPERF_SERVER_METRICS_URLS: "http://localhost:8000/metrics"
     AIPERF_REQUIRED_SERVER_METRIC_PREFIX: "vllm:"
     RESULT_DIR: "/logs/agentic"
     PORT: "8000"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-agentic.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-agentic.yaml
index 0119d7921..97d4d71af 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-agentic.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-agentic.yaml
@@ -96,12 +96,12 @@ srun_options:
 
 benchmark:
   type: custom
-  aiperf_server_metrics: true
   command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh
   env:
     INFMAX_CONTAINER_WORKSPACE: "/infmax-workspace"
     AIPERF_TRACE_IDLE_GAP_CAP_SECONDS: "300"
     AIPERF_LIVE_FAILED_REQUEST_THRESHOLD: "0.25"
+    AIPERF_SERVER_METRICS_URLS: "http://localhost:8000/metrics"
     AIPERF_REQUIRED_SERVER_METRIC_PREFIX: "vllm:"
     RESULT_DIR: "/logs/agentic"
     PORT: "8000"
diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-eval-agentic.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-eval-agentic.yaml
index a3ae8342b..0d50ff7ec 100644
--- a/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-eval-agentic.yaml
+++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-vllm-simple-offload-dspark-eval-agentic.yaml
@@ -94,12 +94,12 @@ srun_options:
 
 benchmark:
   type: custom
-  aiperf_server_metrics: true
   command: bash /infmax-workspace/benchmarks/multi_node/agentic_srt.sh
   env:
     INFMAX_CONTAINER_WORKSPACE: "/infmax-workspace"
     AIPERF_TRACE_IDLE_GAP_CAP_SECONDS: "300"
     AIPERF_LIVE_FAILED_REQUEST_THRESHOLD: "0.25"
+    AIPERF_SERVER_METRICS_URLS: "http://localhost:8000/metrics"
     AIPERF_REQUIRED_SERVER_METRIC_PREFIX: "vllm:"
     RESULT_DIR: "/logs/agentic"
     PORT: "8000"
diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml
index c752b04f6..596bb8205 100644
--- a/configs/nvidia-master.yaml
+++ b/configs/nvidia-master.yaml
@@ -8051,9 +8051,9 @@ kimik3-fp4-b200-dynamo-vllm-agentic-dspark:
     agentic-coding:
     - dram-utilization: 0.63
       search-space:
-      # Low-latency and high-interactivity points.
+      # Retained resident latency curve from the completed broad fast sweep.
       - spec-decoding: mtp
-        conc-list: [1, 2, 4]
+        conc-list: [2, 4, 8, 12]
         prefill:
           num-worker: 1
           tp: 8
@@ -8067,44 +8067,12 @@ kimik3-fp4-b200-dynamo-vllm-agentic-dspark:
           tp: 8
           ep: 16
           dp-attn: true
-      # Balanced medium-concurrency points.
-      - spec-decoding: mtp
-        conc-list: [8, 12, 16]
-        prefill:
-          num-worker: 1
-          tp: 8
-          ep: 16
-          dp-attn: true
-          additional-settings:
-          - "CONFIG_FILE=recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-agentic.yaml"
-          - "EVAL_CONFIG_FILE=recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-eval-agentic.yaml"
-        decode:
-          num-worker: 0
-          tp: 8
-          ep: 16
-          dp-attn: true
-      # GPU-resident throughput points around the prior c16-c32 KV cliff.
-      - spec-decoding: mtp
-        conc-list: [20, 24, 28, 32]
-        prefill:
-          num-worker: 1
-          tp: 8
-          ep: 16
-          dp-attn: true
-          additional-settings:
-          - "CONFIG_FILE=recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-agentic.yaml"
-          - "EVAL_CONFIG_FILE=recipes/vllm/kimi-k3/agentic/agg-b200-tp8dp2-latency-dspark-eval-agentic.yaml"
-        decode:
-          num-worker: 0
-          tp: 8
-          ep: 16
-          dp-attn: true
-      # CPU KV-offload crossover and capacity points. Keep the resident points
-      # above so the same concurrency can be compared with one variable changed.
+      # Retain the measured SimpleCPUOffloadConnector knee, immediate boundary,
+      # and high-capacity controls from the completed broad fast sweep.
       - spec-decoding: mtp
         kv-offloading: dram
         kv-offload-backend: { name: vllm-simple, version: "13c59a3" }
-        conc-list: [8, 12, 16, 20, 24, 28, 32, 48, 64]
+        conc-list: [8, 12, 16, 28, 32, 48]
         prefill:
           num-worker: 1
           tp: 8
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 0bce8d894..7ba903ef4 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -5818,3 +5818,10 @@
   description:
     - "Extend the SimpleCPUOffloadConnector grid to c8/c12/c16/c20/c24/c28/c32/c48/c64 to locate its crossover against the resident curve"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2475
+
+- config-keys:
+    - kimik3-fp4-b200-dynamo-vllm-agentic-dspark
+  description:
+    - "Fix AIPerf server-metrics configuration for the pinned Kimi K3 srt-slurm renderer by passing the aggregate vLLM endpoint through the supported custom-benchmark environment contract"
+    - "After the complete 19-point AgentX-fast search, retain resident c2/c4/c8/c12 and SimpleCPUOffloadConnector c8/c12/c16/c28/c32/c48 for the full-duration latency curve, knee, cliff boundary, and high-capacity controls"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2569