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 ({\Delta}Score = 3.5, Cohen's d_z = 2.53, p < 0.001), followed by plasticity ({\Delta}Score = 3.4, d_z = 1.86), ranked-choice voting ({\Delta}Score = 2.4, d_z = 1.20), and token penalties ({\Delta}Score = 2.2, d_z = 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.
翻译:我们提出Lark,一个受生物学启发的决策框架,它将LLM驱动的推理与进化的、利益相关者感知的多智能体系统(MAS)相结合。为应对冗长性和利益相关者权衡问题,我们整合了四种机制:(i)可塑性,对候选解决方案进行简洁调整;(ii)复制与成熟,复制高性能候选方案并将其专门化为新模块;(iii)使用影响力加权Borda计分的排序选择式利益相关者偏好聚合;(iv)通过基于token的惩罚机制实现计算感知,以奖励简洁性。该系统迭代地提出多样化策略,应用可塑性微调,模拟利益相关者评估,聚合偏好,选择最优候选方案,并执行复制/成熟过程,同时将计算成本纳入最终评分。在包含30轮、比较14个系统的受控评估中,Lark完整版取得了2.55的平均排名(95% CI [2.17, 2.93])和29.4/50的平均综合得分(95% CI [26.34, 32.46]),在80%的轮次中位列前三,同时保持与领先商业模型相当的成本竞争力(每任务$0.016)。配对Wilcoxon检验证实所有四种机制均有显著贡献:消融复制/成熟机制导致最大性能下降(ΔScore = 3.5, Cohen's d_z = 2.53, p < 0.001),其次为可塑性机制(ΔScore = 3.4, d_z = 1.86)、排序选择投票机制(ΔScore = 2.4, d_z = 1.20)和token惩罚机制(ΔScore = 2.2, d_z = 1.63)。Lark并非采用带约束优化的形式化马尔可夫决策过程,而是一个实用的、计算感知的神经进化循环,可扩展利益相关者对齐的策略生成,并通过每步指标使权衡过程透明化。本研究提供了概念验证结果,并邀请社区反馈,以推动我们向真实世界验证研究拓展。