We have 3 of 26 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.
TokenCast is proposed, which learns a composable cost representation for each execution segment, recording its own consumption and the context growth it introduces, and captures the extra input cost incurred when context from earlier segments is re-read by every later call.
This work proposes a novel framework, Multi-Path Causal Optimization (MuPlon), which combines a dual causal intervention strategy, consisting of the back-door path and front-door path, and demonstrates that MuPlon outperforms existing methods and achieves state-of-the-art performance.
A new harness self-evolution method, named DREvo, is proposed, which integrates function-level evidence anchoring, state-dependent evidence recalibration, and role-conditioned search intent distillation to determine which historical evidence remains valid and where the harness should evolve next.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
