AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks

arXiv:2609.38288v1 Announce Type: new Abstract: We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rests on two complementary capabilities: reflection, which produces a solution better than the current one, and long-horizon execution, which keeps the iteration effective…