We have 5 of 7 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.
The proposed MarginFlow framework is a framework that turns the design of the proposal into a learning problem and amortizes it across margins by exploiting their self-similarity.
Loading reusable skill documents into a bounded context window has become a primary way large language model (LLM) agents acquire task-specific capabilities, which makes skill selection a first-order determinant of task performance and token cost. Yet current agents score skills independently by semantic relevance and...
FlexLoop is proposed, a novel post-training framework that converts pretrained fixed-depth looped policies into depth-elastic policies that supports reliable inference across recurrent depths and enables state-wise adaptive inference through recurrent-depth consistency.
It is shown that the frozen agent LLM already carries the routing signal in its own forward passes, and that two linear maps suffice to read it out with no skill text in the context, and Gavel (Glance And Verdict from a frozen LLM) reads it in two steps.
The proposed Module Level Reward Evolution Framework integrates three mechanisms: reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback, which together improve the effectiveness and robustness of reward optimization.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
