add system_message to llm_feedback evaluator

Author: Weaverzhu

examples/circle_packing/config_llm_feedback.yaml

@@ -0,0 +1,61 @@
+# Configuration for circle packing constructor evolution (n=26)
+max_iterations: 100  # Increased iterations
+checkpoint_interval: 10
+log_level: "INFO"
+
+# LLM configuration
+llm:
+  primary_model: "google/gemini-2.0-flash-001"
+  # primary_model: "llama3.1-8b"
+  primary_model_weight: 0.8
+  secondary_model: "anthropic/claude-3.7-sonnet"
+  # secondary_model: "llama-4-scout-17b-16e-instruct"
+  secondary_model_weight: 0.2
+  api_base: "https://openrouter.ai/api/v1"
+  # api_base: "https://api.cerebras.ai/v1"
+  temperature: 0.7
+  top_p: 0.95
+  max_tokens: 8192
+  timeout: 600 
+
+# Prompt configuration
+prompt:
+  system_message: |
+    You are an expert mathematician specializing in circle packing problems and computational geometry. Your task is to improve a constructor function that directly produces a specific arrangement of 26 circles in a unit square, maximizing the sum of their radii. The AlphaEvolve paper achieved a sum of 2.635 for n=26.
+
+    Key geometric insights:
+    - Circle packings often follow hexagonal patterns in the densest regions
+    - Maximum density for infinite circle packing is pi/(2*sqrt(3)) ≈ 0.9069
+    - Edge effects make square container packing harder than infinite packing
+    - Circles can be placed in layers or shells when confined to a square
+    - Similar radius circles often form regular patterns, while varied radii allow better space utilization
+    - Perfect symmetry may not yield the optimal packing due to edge effects
+
+    Focus on designing an explicit constructor that places each circle in a specific position, rather than an iterative search algorithm.
+  num_top_programs: 3
+  use_template_stochasticity: true
+
+# Database configuration
+database:
+  population_size: 60  # Increased population for more diversity
+  archive_size: 25
+  num_islands: 4
+  elite_selection_ratio: 0.3
+  exploitation_ratio: 0.7
+
+# Evaluator configuration
+evaluator:
+  timeout: 60
+  cascade_evaluation: true
+  cascade_thresholds: [0.5, 0.75]
+  parallel_evaluations: 4
+  use_llm_feedback: true
+  system_message: |
+    You are an expert mathematician specializing in circle packing problems and computational geometry. Your task is to be an expert evaluator of a solution to the circle packing problem.
+    You will be given a solution to the circle packing problem and you will need to evaluate it based on the following criteria:
+    - The solution is a valid circle packing of 26 circles in a unit square.
+    
+
+# Evolution settings
+diff_based_evolution: false  # Use full rewrites instead of diffs
+allow_full_rewrites: true    # Allow full rewrites for constructor functions

openevolve/config.py

@@ -104,6 +104,7 @@ class EvaluatorConfig:
     # LLM-based feedback
     use_llm_feedback: bool = False
     llm_feedback_weight: float = 0.1
+    system_message: Optional[str] = None
 
 
 @dataclass

openevolve/evaluator.py

@@ -293,7 +293,10 @@ async def _llm_evaluate(self, program_code: str) -> Dict[str, float]:
             """
 
             # Get LLM response
-            response = await self.llm_ensemble.generate(prompt)
+            response = await self.llm_ensemble.generate_with_context(
+                system_message=self.config.system_message,
+                messages=[{"role": "user", "content": prompt}],
+            )
 
             # Extract JSON from response
             try: