Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
Openevolve: an open-source evolutionary coding agent
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
AEvo introduces a meta-agent that edits the evolution procedure or agent context based on accumulated state, outperforming baselines by 26% relative improvement on agentic benchmarks and achieving SOTA on open-ended tasks.
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
Current AI agents fail to reliably invent transferable ML methods on a controlled 140-task benchmark, and more test-time compute or context does not remove the scientific-judgment bottleneck.
LLM-reinforced evolutionary search produces exact values Z(11,21,3,3)=116, Z(11,22,3,3)=121, Z(12,22,3,3)=132 and lower bounds for 41 additional Zarankiewicz numbers.
Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.
CodeEvolve uses runtime-guided target selection and MCTS-augmented LLM evolution to optimize real Java and Apex code, reporting 15.22x average speedup on seven hotspots while preserving correctness.
citing papers explorer
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
Harnessing Agentic Evolution
AEvo introduces a meta-agent that edits the evolution procedure or agent context based on accumulated state, outperforming baselines by 26% relative improvement on agentic benchmarks and achieving SOTA on open-ended tasks.
-
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
-
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Current AI agents fail to reliably invent transferable ML methods on a controlled 140-task benchmark, and more test-time compute or context does not remove the scientific-judgment bottleneck.
-
New Bounds for Zarankiewicz Numbers via Reinforced LLM Evolutionary Search
LLM-reinforced evolutionary search produces exact values Z(11,21,3,3)=116, Z(11,22,3,3)=121, Z(12,22,3,3)=132 and lower bounds for 41 additional Zarankiewicz numbers.
-
When Does Continual Learning Require Learning
Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.
-
CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement
CodeEvolve uses runtime-guided target selection and MCTS-augmented LLM evolution to optimize real Java and Apex code, reporting 15.22x average speedup on seven hotspots while preserving correctness.