Can evolutionary search beat sampling and revision at inference time?
Can LLMs evolve populations of solutions through recombination and selection to outperform simpler inference strategies? This matters because it could reveal whether biological-inspired search improves planning without formal problem definitions.
Mind Evolution is an evolutionary search strategy for LLM inference that evolves a diverse population of candidate solutions. The LLM generates, recombines, and refines candidates based on evaluator feedback. This is analogous to combining divergent thinking (free-flowing parallel exploration) with convergent thinking (evaluation and selection) — considered hallmarks of intelligent problem-solving.
The key advantage over previous inference strategies: Mind Evolution works in natural language spaces without requiring task formalization. It only needs a programmatic solution evaluator — exploiting the observation that evaluating a candidate solution is often easier than generating one. This removes the need for formal problem definitions, expert-designed search spaces, or auxiliary verifiers.
Three mechanisms drive effectiveness:
- Population diversity via island model: Distinct sub-populations evolve independently between migration and reset events. Migration moves high-fitness solutions across islands; island reset replaces low-fitness populations with strong solutions from the global pool. This sustains exploration diversity that single-population evolution loses.
- LLM-based genetic operators: Instead of traditional mutation and crossover on symbolic representations, the LLM itself recombines and refines candidates using natural language understanding. This enables meaningful variation in unstructured solution spaces.
- Fitness-proportional selection: Parents with greater fitness are more likely to be selected for recombination, creating progressive quality improvement.
On TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of problem instances using Gemini 1.5 Pro — significantly outperforming Best-of-N and Sequential Revision when controlling for inference cost.
This extends the test-time compute landscape beyond the standard parallel-vs-sequential tradeoff. Mind Evolution is neither pure parallel sampling (Best-of-N) nor pure sequential refinement — it is iterative population evolution that combines elements of both. The island model specifically addresses the diversity collapse problem that Do iterative refinement methods suffer from overthinking? identifies — by maintaining multiple independent populations, evolution sustains exploration where single-trajectory refinement converges prematurely.
Inquiring lines that use this note as a source 32
This note is a source for these synthesized inquiries. Follow a line forward into its question, or open it to trace back to all of its sources.
- Why do foundation models develop heuristics instead of world models?
- Can closed-form solutions compete with gradient descent optimization?
- Do dynamic environments enable different kinds of agent-environment coevolution?
- How do evolutionary archives enable diverse exploration in self-improving systems?
- What makes external diversity more effective than sequential revision steps?
- Why do evolutionary algorithms collapse to single solutions under selection pressure?
- What makes diffusion sampling preserve multiple optimal solutions better than alternatives?
- How does latent space diffusion enable evolutionary search in high dimensions?
- Can accelerated sampling techniques from image generation speed up evolutionary search?
- Can evolutionary approaches avoid the overthinking failure mode of iterative refinement?
- How does fitness-proportional selection guide LLM recombination in unstructured solution spaces?
- Why does island model genetic evolution maintain diversity better than single populations?
- Does population-based evolution transcend the parallel versus sequential compute tradeoff?
- Why do parallel and sequential test-time search methods produce equivalent results under fixed budgets?
- Can structural diversity through role assignment replace emergent diversity in small models?
- Why does genetic programming outperform direct LLM generation by 86 percent?
- Can evolutionary search solve persona diversity better than prompt engineering?
- Can optimization algorithms exploit the shift between procedural and planning bottlenecks?
- Can token probability distributions extend swarm composition across different model architectures?
- How does graph-based tool sampling differ from random sampling in diversity?
- What distinguishes intrinsic search from extrinsic search method approaches?
- How should organizations redesign workflows if LLMs cannot solve optimization directly?
- Why does the hot-path cold-path split map onto formation and evolution?
- How does directional diversity compare to other forms of parallel planning?
- Can models adapt and combine search strategies beyond their training algorithm?
- Should test-time search maximize diversity of competent solutions instead of converging on one strategy?
- Is agentic efficiency analogous to convergent evolution in biology?
- Can backward planning reduce search difficulty when multiple goal state paths exist?
- Does policy entropy collapse prevent inference-time search from finding solutions?
- Can evolutionary search unlock problems that best-of-n selection cannot solve?
- Why do automated evaluators enable longer evolutionary loops than human feedback?
- Can the same problem be solved by multiple evolutionary search strategies?
Related concepts in this collection 4
This note in its neighbourhood — explore the map, then jump to a related concept in the list below.
Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph
-
Why does majority voting outperform more complex inference methods?
Simple majority voting across independent samples often matches or beats sophisticated alternatives like Best-of-N and sequential revision. What makes this basic approach so hard to beat for reasoning models?
Mind Evolution goes beyond voting: population-based recombination rather than just aggregation
-
Do iterative refinement methods suffer from overthinking?
Iterative refinement approaches like Self-Refine structurally resemble token-level overthinking in o1-like models. Does revision across multiple inference calls reproduce the same accuracy degradation seen within single inferences?
evolutionary approach avoids this through population diversity and island model
-
How should we balance parallel versus sequential compute at test time?
Test-time compute can prioritize breadth (trying many approaches) or depth (refining one approach). Which strategy works better, and does the answer depend on the problem?
Mind Evolution transcends this dichotomy: iterative evolution with parallel sub-populations
-
Can tree search replace human feedback in LLM training?
Explores whether Monte Carlo Tree Search can generate quality signals for self-improvement without expensive human annotations. Matters because annotation bottlenecks currently limit LLM scaling.
MCTS searches a tree; Mind Evolution searches a population; both use structured exploration
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- Evolving Deeper LLM Thinking
- Learning to Discover at Test Time
- Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- Reasoning LLMs are Wandering Solution Explorers
- A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
Original note title
evolutionary search at inference time outperforms best-of-n and sequential revision on natural language planning