Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits
[Sztuczna inteligencja] Autorzy: Changye Li, Zijian Zhang, Muheng Li i 12 więcej
Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnesses that manage tools, skills, and accumulated experience. However, we find that as single-session execution lengthens, the agent's reasoning intensity declines alongside slowing progress, summarized as long-horizon deceleration, and the benefits of these custom harnesses vanish as the underlying model improves, summarized as harness staleness. These findings suggest that their benefits may not persist across versions, which motivates a workflow-level approach in which agents build on one another's work across sessions. We model these alternating agent sessions as a context-reset semi-Markov decision process (CR-SMDP) and establish sufficient conditions for alternation to exceed single-agent reference limits, derive an explicit experimen…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja