2 papers
cs.AI2026
More Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum
Chenjie Qiu, Boyan Xu, Shaobin Shi +3
Self-evolving agents rewrite a persistent state from feedback, but it is largely untested whether this lets them learn a rule nobody told them. An agent can also pass by writing do…
cs.AI2026
Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation
Chenjie Qiu, Zixuan Zeng, Shaobin Shi +3
Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain embeddi…