diff --git a/benchmark/README.md b/benchmark/README.md
index 930a5ec1..0522b09e 100644
--- a/benchmark/README.md
+++ b/benchmark/README.md
@@ -52,6 +52,7 @@ python download.py            # saves dataset/longmemeval_s_reme_cleaned.json; s
 **BEAM** (public repository, cloned into `benchmark/beam/dataset/`):
 
 ```bash
+mkdir -p benchmark/beam/dataset
 cd benchmark/beam/dataset
 git clone https://github.com/mohammadtavakoli78/BEAM.git
 ```
diff --git a/benchmark/README_ZH.md b/benchmark/README_ZH.md
index cf4c4bbb..0ac8fd3e 100644
--- a/benchmark/README_ZH.md
+++ b/benchmark/README_ZH.md
@@ -48,6 +48,7 @@ python download.py            # 保存为 dataset/longmemeval_s_reme_cleaned.jso
 **BEAM**（公开仓库，clone 到 `benchmark/beam/dataset/` 下）：
 
 ```bash
+mkdir -p benchmark/beam/dataset
 cd benchmark/beam/dataset
 git clone https://github.com/mohammadtavakoli78/BEAM.git
 ```
diff --git a/reme/config/beam.yaml b/reme/config/beam.yaml
index cf7981fc..430bb743 100644
--- a/reme/config/beam.yaml
+++ b/reme/config/beam.yaml
@@ -170,6 +170,28 @@ jobs:
         # chunking in the index.) <= 0 disables splitting.
         max_segment_words: 10000
 
+  # ── Text compression (direct LLM call, no agent) ──
+  compressor:
+    backend: base
+    description: "Compress text via a direct LLM call, optionally guided by queries as relevance filter"
+    parameters:
+      type: object
+      properties:
+        text:
+          type: string
+          description: "the text to compress"
+        queries:
+          type: array
+          description: "optional list of queries; content potentially relevant to any query is kept, content certainly irrelevant to all queries may be dropped"
+          items:
+            type: string
+          default: []
+      required:
+        - text
+    steps:
+      - backend: compressor_step
+        as_llm: compressor
+
   # ── Reindex (full rebuild) ──
   reindex:
     backend: base
@@ -516,6 +538,19 @@ components:
       parameters:
         max_tokens: 65536
         thinking_enable: true
+    compressor:
+      backend: ${LLM_BACKEND:-openai}
+      model: ${LLM_MODEL_NAME:-qwen3.6-flash}
+      stream: false
+      context_size: 200000
+      max_retries: 5
+      retry_delay: 5.0
+      credential:
+        api_key: ${LLM_API_KEY:-}
+        base_url: ${LLM_BASE_URL:-}
+      parameters:
+        max_tokens: 65536
+        thinking_enable: false
 
   agent_wrapper:
     default:
diff --git a/reme/steps/index/search_v2.py b/reme/steps/index/search_v2.py
index b9e7581a..02462a76 100644
--- a/reme/steps/index/search_v2.py
+++ b/reme/steps/index/search_v2.py
@@ -258,8 +258,26 @@ class SearchV2Step(_ToolContextDedupMixin, BaseStep):
         succeeded and the result is not longer than the input; adopted bodies
         get a leading ``compressed session chunk:`` marker so downstream
         consumers can tell them from verbatim transcripts.
+
+        Degrades gracefully when the ``compressor`` job is missing from the
+        active config: the whole method becomes a no-op and a warning is
+        logged, so search behaves as if compression were disabled. This
+        avoids a hard ``Job compressor not found`` failure when a benchmark
+        config forgets to define the compressor job/component.
         """
         assert self.context is not None
+        # Guard: when the compressor job is missing from the active config
+        # (e.g. a benchmark config that forgot to define it), degrade
+        # gracefully to the no-compression behavior instead of raising
+        # "Job compressor not found" from run_job below.
+        # Skipped when there is no app_context (e.g. unit tests that mock
+        # run_job directly), so the mock can still drive compression.
+        if self.app_context is not None and self.get_job("compressor") is None:
+            self.logger.warning(
+                f"[{self.name}] compressor job not found in config; "
+                "skipping session chunk compression (degrading to uncompressed behavior)",
+            )
+            return
         search_cfg: dict = self.context.get("_search") or {}
         query_type = str(search_cfg.get("type") or "query-aware").strip().lower()
         if query_type == "query-independent":