AgentSpawn: 通过动态生成实现长周期代码生成的自适应多智能体协作
AgentSpawn: Adaptive Multi-Agent Collaboration Through Dynamic Spawning for Long-Horizon Code Generation
AI总结:
AgentSpawn通过动态生成实现长周期代码生成的自适应多智能体协作,提升完成率并降低内存开销。
摘要:
长周期代码生成需要持续的上下文和跨领域的适应性专业知识。当前的多智能体系统使用静态工作流,当运行时分析揭示出未预料的复杂性时无法适应。我们提出AgentSpawn,一种通过:(1)在生成过程中自动传输内存,(2)由运行时复杂度度量触发的自适应生成策略,以及(3)用于同时修改的协议的架构。AgentSpawn解决了现有研究中关于内存连续性、技能继承、任务恢复、运行时生成和同时一致性五个关键缺口。实验验证显示,AgentSpawn在SWE-bench等基准测试中比静态基线高出34%的完成率,同时通过选择性切片减少了42%的内存开销。
英文摘要:
Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn, an architecture enabling dynamic agent collaboration through: (1) automatic memory transfer during spawning, (2) adaptive spawning policies triggered by runtime complexity metrics, and (3) coherence protocols for concurrent modifications. AgentSpawn addresses five critical gaps in existing research around memory continuity, skill inheritance, task resumption, runtime spawning, and concurrent coherence. Experimental validation demonstrates AgentSpawn achieves 34% higher completion rates than static baselines on benchmarks like SWE-bench while reducing memory overhead by 42% through selective slicing.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。