We have 3 of 68 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.
Cold-Start Failure-Only Evolution reveals that current self-evolving agents are better at repairing observed failures than building generalizable capabilities from failure, and suggests that current self-evolving agents are better at repairing observed failures than building generalizable capabilities from failure.
LSR-Ben is introduced, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (scientific and logical reasoning) and nine subdomains and it is hoped LSR-Ben can foster future researches on PRMs for broader domains, thereby enhancing the reasoning capabilitie...
Experiments on challenging reasoning benchmarks show that H$^2$SD achieves the strongest overall performance among representative RLVR and self-distillation baselines, with stable optimization and a favorable accuracy-efficiency trade-off.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
