Add all-methods comparison table with dataset caveat

- Add vanilla/contextual/all_memory from fullscale (different datasets)
- Flag dataset mismatch (5-dataset vs 3-dataset)
- Queue matching-dataset vanilla/contextual experiment
- Same-dataset comparison: rag_vector leads in success (54.2%)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

1 files changed, 46 insertions, 0 deletions

diff --git a/collaborativeagents/scripts/queue_baselines_60s.sh b/collaborativeagents/scripts/queue_baselines_60s.sh
new file mode 100755
index 0000000..0938ff4
--- /dev/null
+++ b/collaborativeagents/scripts/queue_baselines_60s.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+# Run vanilla and contextual baselines with matching datasets (math-hard, math-500, bigcodebench)
+# Same setup as rag/reflection/rag_vector 60s experiments for fair comparison
+
+echo "Starting baseline experiments (vanilla + contextual)..."
+echo "$(date '+%Y-%m-%d %H:%M:%S')"
+
+# Vanilla (no personalization)
+echo "Starting vanilla..."
+python collaborativeagents/scripts/run_experiments.py \
+    --methods vanilla \
+    --datasets math-hard,math-500,bigcodebench \
+    --n-profiles 60 \
+    --n-sessions 60 \
+    --max-turns 10 \
+    --use-vllm \
+    --vllm-agent-url http://localhost:8003/v1 \
+    --vllm-user-url http://localhost:8004/v1 \
+    --use-batch-processing \
+    --batch-size 4 \
+    --parallel-profiles 20 \
+    --profile-path collaborativeagents/data/complex_profiles_v2/profiles_200.jsonl \
+    --output-dir collaborativeagents/results/vanilla_60s \
+    2>&1 | tee collaborativeagents/results/vanilla_60s.log
+
+echo "Vanilla completed at $(date '+%Y-%m-%d %H:%M:%S')"
+
+# Contextual (full history in context)
+echo "Starting contextual..."
+python collaborativeagents/scripts/run_experiments.py \
+    --methods contextual \
+    --datasets math-hard,math-500,bigcodebench \
+    --n-profiles 60 \
+    --n-sessions 60 \
+    --max-turns 10 \
+    --use-vllm \
+    --vllm-agent-url http://localhost:8003/v1 \
+    --vllm-user-url http://localhost:8004/v1 \
+    --use-batch-processing \
+    --batch-size 4 \
+    --parallel-profiles 20 \
+    --profile-path collaborativeagents/data/complex_profiles_v2/profiles_200.jsonl \
+    --output-dir collaborativeagents/results/contextual_60s \
+    2>&1 | tee collaborativeagents/results/contextual_60s.log
+
+echo "Both baselines completed at $(date '+%Y-%m-%d %H:%M:%S')"