make it simpler

Author: codelion

examples/circle_packing/README.md

@@ -1,20 +1,18 @@
-# Circle Packing Example
+# Circle Packing Example (n=26)
 
-This example attempts to replicate one of the results from the AlphaEvolve paper (Section B.12): packing circles inside a unit square to maximize the sum of their radii.
+This example attempts to replicate one of the specific results from the AlphaEvolve paper (Section B.12): packing 26 circles inside a unit square to maximize the sum of their radii.
 
 ## Problem Description
 
-Given a positive integer n, the problem is to pack n disjoint circles inside a unit square so as to maximize the sum of their radii. The circles must:
+The problem is to pack 26 disjoint circles inside a unit square so as to maximize the sum of their radii. The circles must:
 - Lie entirely within the unit square [0,1] × [0,1]
 - Not overlap with each other
 
 This is a well-studied problem in computational geometry with applications in various fields including material science, facility location, and computer graphics.
 
-## AlphaEvolve Results
+## AlphaEvolve Result
 
-According to the paper, AlphaEvolve found new constructions improving the state of the art:
-- For n = 26, improved from 2.634 to 2.635
-- For n = 32, improved from 2.936 to 2.937
+According to the paper, AlphaEvolve improved the state of the art for n=26 from 2.634 to 2.635.
 
 ## Running the Example
 
@@ -25,16 +23,25 @@ python openevolve-run.py examples/circle_packing/initial_program.py examples/cir
 ## Evaluation Metrics
 
 The evaluator calculates several metrics:
-- `sum_radii_26`: Sum of radii for n=26
-- `sum_radii_32`: Sum of radii for n=32
-- `target_ratio_26`: Ratio of achieved sum to target (2.635) for n=26
-- `target_ratio_32`: Ratio of achieved sum to target (2.937) for n=32
-- `validity`: 1.0 if solutions for both n=26 and n=32 are valid, 0.0 otherwise
-- `avg_target_ratio`: Average of target ratios
-- `combined_score`: avg_target_ratio * validity (main fitness metric)
+- `sum_radii`: The best sum of radii achieved across all trials
+- `avg_sum_radii`: Average sum of radii across successful trials
+- `target_ratio`: Ratio of achieved sum to target (2.635)
+- `reliability`: Fraction of trials that produced valid solutions
+- `avg_time`: Average execution time
+- `combined_score`: A weighted combination of the above metrics (main fitness metric)
 
 ## Expected Results
 
-A successful run should find packing arrangements with sums approaching or exceeding the values reported in the AlphaEvolve paper:
-- n=26: 2.635
-- n=32: 2.937
+A successful run should find a packing arrangement with sum of radii approaching or exceeding the value reported in the AlphaEvolve paper: 2.635 for n=26.
+
+## Visualization
+
+The initial program includes a visualization function that you can use to see the packing arrangement:
+
+```python
+# Add this to the end of the best program
+if __name__ == "__main__":
+    centers, radii, sum_radii = run_packing()
+    print(f"Sum of radii: {sum_radii}")
+    visualize(centers, radii)
+```

examples/circle_packing/config.yaml

@@ -21,7 +21,7 @@ llm:
 
 # Prompt configuration
 prompt:
-  system_message: "You are an expert programmer specializing in optimization algorithms and computational geometry. Your task is to improve a circle packing algorithm to maximize the sum of radii when packing n circles in a unit square without overlaps. The AlphaEvolve paper achieved a sum of 2.635 for n=26 and 2.937 for n=32. Focus on finding better optimization strategies to reach or exceed these values."
+  system_message: "You are an expert programmer specializing in optimization algorithms and computational geometry. Your task is to improve a circle packing algorithm to maximize the sum of radii when packing 26 circles in a unit square without overlaps. The AlphaEvolve paper achieved a sum of 2.635 for n=26, which is the target value to reach or exceed. Focus on finding better optimization strategies, leveraging geometric insights about optimal packing arrangements, and developing more effective search techniques."
   num_top_programs: 3
   use_template_stochasticity: true