SOURCE-LINKED INTELLIGENCE
What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints. Evaluating across sampling breadth $K$ and interaction depth $T$ via $Pass@(K,T)$, we show that trajectory-level RL advantages depend on sufficient turn budgets, diminishing significantly when budgets tighten. Besides, agentic RL does not uniformly elevate single-step decision quality; rather, its strength concentrates in error recovery and long-horizon resilience. To mitigate the deployment risks caused by this budget dependence, we provi
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-11-04T13:24:54.000Z
First collected: 2026-11-05T14:44:11.081Z. This is not the publication date.