HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning
Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs. Leading approaches such as the Darwin--Godel Machine and the Huxley--Godel Machine (HGM) rely on recursive self-improvement and were developed mainly for coding, where the competence needed to improve the agent coincides with the competence being improved. Planning tasks, in which an agent must produce a sequence of tool calls that jointly satisfies interacting constraints, break this alignment. There, open-ended self-modification repeatedly explores ineffective changes and consumes substantial evaluation budgets. We introduce HGM-Dual, a diagnostic-guided framework for budget-efficient harness evolution for planning agents
为规划任务优化代理，减少无效自我修改的消耗。
- 核心方法
- 提出了HGM-Dual框架，通过诊断引导的方式，实现对规划代理的有效预算优化进化。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 现有方法在规划任务中由于需要开放式的自我修改，导致对评估预算的大量消耗。
- 关键实验
- 未提供
- 主要贡献
- 提供了一种在规划任务中进行高效代理优化的方法，减少了评估预算的浪费。
- 意义与局限
- HGM-Dual框架可能显著改善长期规划任务中代理的性能和效率，但其适用范围和实际效果仍需通过具体实验验证。