Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
论文揭示不可靠反馈如何破坏LLM代理的工具使用能力,提醒不要盲目信任反馈机制。
arXiv:2606.21409v1 Announce Type: new Abstract: Tool-augmented agents are typically evaluated by their gains under reliable external feedback. Yet the…