Self-Evaluating Recursive Agents
SEMA (Self-Evaluating Recursive Agents) turns evaluation into a learned capability of the policy itself, which sharpens the agent's ability to solve subtasks and doubles as an inference-time selector for tree search.
We have 2 of 13 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.
SEMA (Self-Evaluating Recursive Agents) turns evaluation into a learned capability of the policy itself, which sharpens the agent's ability to solve subtasks and doubles as an inference-time selector for tree search.
By decoupling action proposal from consequence evaluation, SVA preserves the generalization capacity of the VLA backbone while substantially improving task success rates, and shows that SVA consistently improves generalization on unseen tasks and exhibits strong test-time scaling behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.