Learning to Steer LLM Agents and Multi-Agent Systems
[Uczenie maszynowe] Autorzy: Leyang Shen, Yaxin Gong, Yang Zhang i 7 więcej
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, these systems are prone to deviating from the overall goal as execution unfolds, which wastes execution resources and leads to undesired outcomes, a failure termed goal drift. In this work, we propose a steering agent that supervises execution on the fly and steers the system back on track when drift occurs. The steering agent observes the execution context, deciding when to intervene with a low-cost fast path and how to intervene with a high-cost slow path. To unlock its steering intelligence, the ability to assess goal drift and generate effective interventions, we jointly train the two paths with reinforcement learning, combining a pairwise ranking objective with group-relative policy optimization (GRPO). Experiments o…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe