# LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm

arXiv: https://arxiv.org/abs/2512.24077 · HTML: https://mlsanity.com/paper/2512.24077/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Self-evolving LLM agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)

## Built on by (most cited first, 22 of 22)

- [AVO: Agentic Variation Operators for Autonomous Evolutionary Search](https://mlsanity.com/paper/2603.24517/) (2026)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery](https://mlsanity.com/paper/2606.13662/) (2026)
- [ASI-Evolve: AI Accelerates AI](https://mlsanity.com/paper/2603.29640/) (2026)
- [TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution](https://mlsanity.com/paper/2604.18607/) (2026)
- [Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering](https://mlsanity.com/paper/2606.30911/) (2026)
- [ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization](https://mlsanity.com/paper/2602.02597/) (2026)
- [Harness Engineering for LLM-Driven GPU Kernel Generation](https://mlsanity.com/paper/2607.17979/) (2026)
- [What is Missing from AI Post-Training AI: An Empirical Analysis](https://mlsanity.com/paper/2608.19072/) (2026)
- [Automated near-term quantum algorithm discovery for molecular ground states](https://mlsanity.com/paper/2603.26359/) (2026)
- [k-server-bench: Automating Potential Discovery for the k-Server Conjecture](https://mlsanity.com/paper/2604.07240/) (2026)
- [Agentic Discovery of Exchange-Correlation Density Functionals](https://mlsanity.com/paper/2605.05460/) (2026)
- [Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation](https://mlsanity.com/paper/2608.28886/) (2026)
- [Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning](https://mlsanity.com/paper/2609.22257/) (2026)
- [Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search](https://mlsanity.com/paper/2609.29636/) (2026)
- [HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization](https://mlsanity.com/paper/2609.36303/) (2026)
- [SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents](https://mlsanity.com/paper/2610.02361/) (2026)
- [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026)
- [Assembling Insights for Agentic Machine Learning Engineering Systems](https://mlsanity.com/paper/2610.04927/) (2026)
- [EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution](https://mlsanity.com/paper/2610.12086/) (2026)

## Abstract (arXiv)

The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and inefficient exploration in high-dimensional code spaces. To address these challenges, we introduce LoongFlow, a self-evolving agent framework that achieves state-of-the-art solution quality with significantly reduced computational costs. Unlike "blind" mutation operators, LoongFlow integrates LLMs into a cognitive "Plan-Execute-Summarize" (PES) paradigm, effectively mapping the evolutionary search to a reasoning-heavy process. To sustain long-term architectural coherence, we incorporate a hybrid evolutionary memory system. By synergizing Multi-Island models with MAP-Elites and adaptive Boltzmann selection, this system theoretically balances the exploration-exploitation trade-off, maintaining diverse behavioral niches to prevent optimization stagnation. We instantiate LoongFlow with a General Agent for algorithmic discovery and an ML Agent for pipeline optimization. Extensive evaluations on the AlphaEvolve benchmark and Kaggle competitions demonstrate that LoongFlow outperforms leading baselines (e.g., OpenEvolve, ShinkaEvolve) by up to 60% in evolutionary efficiency while discovering superior solutions. LoongFlow marks a substantial step forward in autonomous scientific discovery, enabling the generation of expert-level solutions with reduced computational overhead.