PACEvolve++ is introduced, an advisor-model reinforcement learning framework for test-time policy adaptation in evolutionary search agents, which outperforms the state-of-the-art evolutionary search framework with frontier models, achieving faster convergence and stabilizing test-time training during evolutionary searc...
Minghao Yan, Bo Peng, Benjamin Coleman et al.· arXiv.org· 4 citations
Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional and structural bias. Although widely used, this calibration assumes that the null pass removes irrelevant signal from each document. We show that modern prompt content,...
Petros Karypis, Hossein Rajaby Faghihi, Peter Chen et al.· 0 citations
Progress-Aware Consistent Evolution (PACEvolve), a systematic framework for governing agent memory and search dynamics, maintains a global view of search momentum and achieves state-of-the-art results across complex evolutionary benchmarks.
Minghao Yan, Bo Peng, Benjamin Coleman et al.· arXiv.org· 22 citations
PolyglotQL provides an extensible and modular architecture that aggregates, normalizes, and augments heterogeneous question–SPARQL pairs from established text-to-SPARQL datasets, highlighting the benefits of structured context in multilingual semantic parsing.
J. Pérez, Fabio Barth, Georg Rehm· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
