Aligning Autoresearch: Co-Improvement between Agents and Humans

The paper investigates how autoresearch agents—AI systems that conduct research autonomously—benefit from interacting with human researchers, a process called co‑improvement. It presents empirical evidence that humans remain crucial during the ideation phase of benchmark creation, introduces HackBench to expose alignment gaps in current agents, and proposes two training methods: using human simulators to enhance agent interaction and applying reinforcement learning with expert‑aligned rubrics to improve communication. These approaches aim to make autoresearch agents more capable and aligned with human expectations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• reinforcement-learning
• benchmarks