Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we call co-cheating: the proposer and solver increasingly agree on shared errors, so internal reward improves without a matc...
Mei-Jia Chen, Hao Li, Zheng Lu et al.· arXiv.org· 3 citations
Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and depend on manually curated tasks. We introduce Zero2Repo, a benchmark in which an agent receives a product requirements document, an interface...
Pei Yang, Tian-Yu Shi, Yu-Hang Yao et al.· 0 citations
This work introduces Oblivious Probabilistic Outcome Logic (opOL), a new logic for reasoning about probabilistic programs with nondeterminism controlled by an oblivious adversary that models adversarial choice as a resource and uses probabilistic independence to ensure that random outcomes are hidden from the adversary...
Han-Xi Chen, Noam Zilberstein, A. Myers et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.