REVIEW 8 cited by
Evolution through Large Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper pursues the insight that large language models (LLMs) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic programming (GP). Because such LLMs benefit from training data that includes sequential changes and modifications, they can approximate likely changes that humans would make. To highlight the breadth of implications of such evolution through large models (ELM), in the main experiment ELM combined with MAP-Elites generates hundreds of thousands of functional examples of Python programs that output working ambulating robots in the Sodarace domain, which the original LLM had never seen in pre-training. These examples then help to bootstrap training a new conditional language model that can output the right walker for a particular terrain. The ability to bootstrap new models that can output appropriate artifacts for a given context in a domain where zero training data was previously available carries implications for open-endedness, deep learning, and reinforcement learning. These implications are explored here in depth in the hope of inspiring new directions of research now opened up by ELM.
Forward citations
Cited by 8 Pith papers
-
ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space
ELFuzz automatically evolves LLM-written input generators for large programs, outperforming grammar-based fuzzers in coverage and bug finding on seven benchmarks.
-
Autonomous Discovery of Wireless Communications Algorithms
AITE, an LLM-driven evolutionary search framework, discovered a low-latency OTFS equalizer and an explicit explainable pilotless OFDM receiver that matches neural receiver performance in simulation.
-
Heuristic Learning for Active Flow Control Using Coding Agents
Under equal simulation budgets, coding-agent search finds explicit flow controllers that match or beat the best DRL baseline on 10 of 13 active-flow-control benchmarks.
-
Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation
Genetic Prompt uses LLMs to run semantic-level crossover and mutation on text attributes from two far-apart parent examples, producing synthetic data that improves downstream NLP performance, especially for rare classes.
-
How Should We Meta-Learn Reinforcement Learning Algorithms?
A systematic comparison of black-box evolution, neural and symbolic distillation, and LLM-based proposal for meta-learning RL algorithms yields practical recommendations: warm-started LLM proposal is sample-efficient,...
-
SPARQ: Synthetic Problem Generation for Reasoning via Quality-Diversity Algorithms
Filtering self-generated math problems by a model's own solve-rate improves that model's MATH accuracy from 38% to 47% and helps out-of-distribution generalization when data is diverse.
-
Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems
Evolutionary intelligence reframes evolutionary computation as cumulative scientific discovery by retaining search trajectories, failures, and lineages across cycles.
-
SAIL: Sound Abstract Interpreters with LLMs
SAIL synthesizes globally sound abstract transformers for neural-network operators by combining LLM generation with syntactic validation, SMT-based soundness checking, and cost-guided iterative refinement.
Discussion (0). Sign in to comment.