EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery

📅 2025-12-15
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing LLM-driven program evolution methods predominantly employ overwrite-style mutation, retaining only a single candidate per iteration—leading to loss of beneficial variants, structural degradation, and poor robustness in fragile search spaces. This paper proposes a directed acyclic graph (DAG)-based multi-alternative population representation: nodes store persistent code fragments, and executable programs correspond to paths through the DAG, enabling structural sharing and combinatorial search. We pioneer implicit encoding of quality-diversity optimization into the graph’s topology; further, we introduce substitution-level statistical evaluation and dependency-aware deterministic self-repair, enhancing structural robustness without compromising LLM-generated flexibility. Experiments demonstrate that our method achieves significantly more stable evolution, greater expressive capacity, and superior performance improvement trajectories on program synthesis and meta-learning tasks—outperforming state-of-the-art LLM-guided evolutionary approaches.

Technology Category

Application Category

📝 Abstract
Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods discard useful variants, suffer from destructive edits, and explore a brittle search space prone to structural failure. We introduce EvoLattice, a framework that represents an entire population of candidate programs or agent behaviors within a single directed acyclic graph. Each node stores multiple persistent alternatives, and every valid path through the graph defines a distinct executable candidate, yielding a large combinatorial search space without duplicating structure. EvoLattice enables fine-grained alternative-level evaluation by scoring each alternative across all paths in which it appears, producing statistics that reveal how local design choices affect global performance. These statistics provide a dense, data-driven feedback signal for LLM-guided mutation, recombination, and pruning, while preserving successful components. Structural correctness is guaranteed by a deterministic self-repair mechanism that enforces acyclicity and dependency consistency independently of the LLM. EvoLattice naturally extends to agent evolution by interpreting alternatives as prompt fragments or sub-agent behaviors. Across program synthesis (proxy and optimizer meta-learning), EvoLattice yields more stable evolution, greater expressivity, and stronger improvement trajectories than prior LLM-guided methods. The resulting dynamics resemble quality-diversity optimization, emerging implicitly from EvoLattice's internal multi-alternative representation rather than an explicit external archive.
Problem

Research questions and friction points this paper is trying to address.

Overcoming destructive mutations in LLM-guided program evolution
Representing entire candidate populations within single graph structures
Ensuring structural correctness while preserving successful components
Innovation

Methods, ideas, or system contributions that make the work stand out.

Persistent internal population stored in directed acyclic graph
Fine-grained alternative-level evaluation across all graph paths
Deterministic self-repair mechanism ensures structural correctness
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
K
Kamer Ali Yuksel
aiXplain Inc, San Jose, USA