# Lark: Biologically Inspired Neuroevolution for Multi-Stakeholder LLM Agents

arXiv: https://arxiv.org/abs/2510.16978 · HTML: https://mlsanity.com/paper/2510.16978/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 19 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 13 of 13)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning](https://mlsanity.com/paper/2504.05108/) (2025)
- [From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users](https://mlsanity.com/paper/2508.17281/) (2025)
- [Large Language Model-Enabled Multi-Agent Manufacturing Systems](https://mlsanity.com/paper/2406.01893/) (2024)
- [ELENA: Epigenetic Learning through Evolved Neural Adaptation](https://mlsanity.com/paper/2501.05735/) (2025)
- [Epigenetic opportunities for Evolutionary Computation](https://mlsanity.com/paper/2108.04546/) (2021)
- [Beyond Predictions: A Participatory Framework for Multi-Stakeholder Decision-Making](https://mlsanity.com/paper/2502.08542/) (2025)
- [Evolutionary thoughts: integration of large language models and evolutionary algorithms](https://mlsanity.com/paper/2505.05756/) (2025)

## Abstract (arXiv)

We present Lark, a biologically inspired decision-making framework that couples LLM-driven reasoning with an evolutionary, stakeholder-aware Multi-Agent System (MAS). To address verbosity and stakeholder trade-offs, we integrate four mechanisms: (i) plasticity, which applies concise adjustments to candidate solutions; (ii) duplication and maturation, which copy high-performing candidates and specialize them into new modules; (iii) ranked-choice stakeholder aggregation using influence-weighted Borda scoring; and (iv) compute awareness via token-based penalties that reward brevity. The system iteratively proposes diverse strategies, applies plasticity tweaks, simulates stakeholder evaluations, aggregates preferences, selects top candidates, and performs duplication/maturation while factoring compute cost into final scores. In a controlled evaluation over 30 rounds comparing 14 systems, Lark Full achieves a mean rank of 2.55 (95% CI [2.17, 2.93]) and a mean composite score of 29.4/50 (95% CI [26.34, 32.46]), finishing Top-3 in 80% of rounds while remaining cost competitive with leading commercial models (0.016 per task). Paired Wilcoxon tests confirm that all four mechanisms contribute significantly as ablating duplication/maturation yields the largest deficit (DeltaScore = 3.5, Cohen's dz = 2.53, p < 0.001), followed by plasticity (DeltaScore = 3.4, dz = 1.86), ranked-choice voting (DeltaScore = 2.4, dz = 1.20), and token penalties (DeltaScore = 2.2, dz = 1.63). Rather than a formal Markov Decision Process with constrained optimization, Lark is a practical, compute-aware neuroevolutionary loop that scales stakeholder-aligned strategy generation and makes trade-offs transparent through per-step metrics. Our work presents proof-of-concept findings and invites community feedback as we expand toward real-world validation studies.