We have 4 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
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...
TwinRouterBench is introduced, a step-level routing benchmark with two tracks that supports fast offline iteration followed by end-to-end validation under live agent execution, and success is measured by official task resolution and realized API spend.
Combee is proposed, a novel framework to scale parallel prompt learning for self-improving agents that speeds up learning and enables running many agents in parallel while learning from their aggregate traces without quality degradation.
Results indicate that verifier-backed multi-cycle adaptation can increase small-model capability, rather than only routing around a fixed student.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
