用多目标优化提升智能体技能，兼顾性能与平台限制。
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
- 采用切比雪夫标量化方法覆盖全帕累托前沿
- 实验显示平均正确率提升7.5%，最高达14.9%
- 适合需要平衡性能与资源约束的智能体开发者
大型语言模型智能体通过技能组织行为——即结构化的自然语言规范，控制智能体的推理、检索与响应。与单体提示不同，技能是受严格平台约束的多字段实体：描述字段受限于路由长度，指令主体需通过渐进披露压缩，共存技能则竞争有限的上下文窗口。这些约束使技能优化本质上为多目标问题：技能需同时最大化任务表现并满足平台限制。现有提示优化器或忽略此类权衡，或将其简化为加权和，遗漏非凸区域的帕累托最优解。本文提出MOCHA（多目标切比雪夫退火），以切比雪夫标量化替代单目标选择，覆盖完整帕累托前沿（包括非凸区域），并结合指数退火实现从探索到利用的过渡。在六种不同智能体技能上的实验表明，所有方法使用相同多目标变异算子，基线获得相同每目标文本反馈，现有优化器在6个任务中有4个任务上1000次回放未见进展；而MOCHA在所有任务上均取得突破，相比最强基线平均正确率提升7.5%（在FEVER上最高达14.9%，TheoremQA上达10.4%），且发现的帕累托最优技能变体数量翻倍。
原文摘要 · Abstract (English)
LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike monolithic prompts, skills are multi-field artifacts subject to hard platform constraints: description fields are truncated for routing, instruction bodies are compacted via progressive disclosure, and co-resident skills compete for limited context windows. These constraints make skill optimization inherently multi-objective: a skill must simultaneously maximize task performance and satisfy platform limits. Yet existing prompt optimizers either ignore these trade-offs or collapse them into a weighted sum, missing Pareto-optimal variants in non-convex objective regions. We introduce MOCHA (Multi-Objective Chebyshev Annealing), which replaces single-objective selection with Chebyshev scalarization - covering the full Pareto front, including non-convex regions - combined with exponential annealing that transitions from exploration to exploitation. In our experiments across six diverse agent skills - where all methods share the same multi-objective mutation operator and baselines receive identical per-objective textual feedback - existing optimizers fail to improve the seed skill on 4 of 6 tasks: 1000 rollouts yield zero progress. MOCHA breaks through on every task, achieving 7.5% relative improvement in mean correctness over the strongest baseline (up to 14.9% on FEVER and 10.4% on TheoremQA) while discovering twice as many more Pareto-optimal skill variants.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。